Predict Bike Sharing Demand with AutoGluon Template

Project: Predict Bike Sharing Demand with AutoGluon

This notebook is a template with each step that you need to complete for the project.

Please fill in your code where there are explicit ? markers in the notebook. You are welcome to add more cells and code as you see fit.

Once you have completed all the code implementations, please export your notebook as a HTML file so the reviews can view your code. Make sure you have all outputs correctly outputted.

File-> Export Notebook As... -> Export Notebook as HTML

There is a writeup to complete as well after all code implememtation is done. Please answer all questions and attach the necessary tables and charts. You can complete the writeup in either markdown or PDF.

Completing the code template and writeup template will cover all of the rubric points for this project.

The rubric contains "Stand Out Suggestions" for enhancing the project beyond the minimum requirements. The stand out suggestions are optional. If you decide to pursue the "stand out suggestions", you can include the code in this notebook and also discuss the results in the writeup file.

Step 1: Create an account with Kaggle

Create Kaggle Account and download API key

Below is example of steps to get the API username and key. Each student will have their own username and key.

1. Open account settings.
2. Scroll down to API and click Create New API Token.
3. Open up kaggle.json and use the username and key.

Step 2: Download the Kaggle dataset using the kaggle python library

Open up Sagemaker Studio and use starter template

1. Notebook should be using a ml.t3.medium instance (2 vCPU + 4 GiB)
2. Notebook should be using kernal: Python 3 (MXNet 1.8 Python 3.7 CPU Optimized)

Install packages

# !pip install -U pip
# !pip install -U setuptools wheel
# !pip install -U "mxnet<2.0.0" bokeh==2.0.1
# !pip install autogluon --no-cache-dir
# # Without --no-cache-dir, smaller aws instances may have trouble installing

Setup Kaggle API Key

# # create the .kaggle directory and an empty kaggle.json file
# !mkdir -p /root/.kaggle
# !touch /root/.kaggle/kaggle.json
# !chmod 600 /root/.kaggle/kaggle.json

# # Fill in your user name and key from creating the kaggle account and API token file
# import json
# kaggle_username = "FILL_IN_USERNAME"
# kaggle_key = "FILL_IN_KEY"

# # Save API token the kaggle.json file
# with open("/root/.kaggle/kaggle.json", "w") as f:
#     f.write(json.dumps({"username": kaggle_username, "key": kaggle_key}))

Download and explore dataset

Go to the bike sharing demand competition and agree to the terms

# # Download the dataset, it will be in a .zip file so you'll need to unzip it as well.
# !kaggle competitions download -c bike-sharing-demand
# # If you already downloaded it you can use the -o command to overwrite the file
# !unzip -o bike-sharing-demand.zip

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from autogluon.tabular import TabularPredictor
import autogluon.core as ag

import warnings
warnings.filterwarnings('ignore')

# Create the train dataset in pandas by reading the csv
# Set the parsing of the datetime column so you can use some of the `dt` features in pandas later
train = pd.read_csv('bike-sharing-demand/train.csv',parse_dates =['datetime'])

train.head()

	datetime	season	holiday	workingday	weather	temp	atemp	humidity	windspeed	casual	registered	count
0	2011-01-01 00:00:00	1	0	0	1	9.84	14.395	81	0.0	3	13	16
1	2011-01-01 01:00:00	1	0	0	1	9.02	13.635	80	0.0	8	32	40
2	2011-01-01 02:00:00	1	0	0	1	9.02	13.635	80	0.0	5	27	32
3	2011-01-01 03:00:00	1	0	0	1	9.84	14.395	75	0.0	3	10	13
4	2011-01-01 04:00:00	1	0	0	1	9.84	14.395	75	0.0	0	1	1

# Simple output of the train dataset to view some of the min/max/varition of the dataset features.

train.describe()

	season	holiday	workingday	weather	temp	atemp	humidity	windspeed	casual	registered	count
count	10886.000000	10886.000000	10886.000000	10886.000000	10886.00000	10886.000000	10886.000000	10886.000000	10886.000000	10886.000000	10886.000000
mean	2.506614	0.028569	0.680875	1.418427	20.23086	23.655084	61.886460	12.799395	36.021955	155.552177	191.574132
std	1.116174	0.166599	0.466159	0.633839	7.79159	8.474601	19.245033	8.164537	49.960477	151.039033	181.144454
min	1.000000	0.000000	0.000000	1.000000	0.82000	0.760000	0.000000	0.000000	0.000000	0.000000	1.000000
25%	2.000000	0.000000	0.000000	1.000000	13.94000	16.665000	47.000000	7.001500	4.000000	36.000000	42.000000
50%	3.000000	0.000000	1.000000	1.000000	20.50000	24.240000	62.000000	12.998000	17.000000	118.000000	145.000000
75%	4.000000	0.000000	1.000000	2.000000	26.24000	31.060000	77.000000	16.997900	49.000000	222.000000	284.000000
max	4.000000	1.000000	1.000000	4.000000	41.00000	45.455000	100.000000	56.996900	367.000000	886.000000	977.000000

# Create the test pandas dataframe in pandas by reading the csv, remember to parse the datetime!
test = pd.read_csv('bike-sharing-demand/test.csv',parse_dates =['datetime'])
test.head()

	datetime	season	holiday	workingday	weather	temp	atemp	humidity	windspeed
0	2011-01-20 00:00:00	1	0	1	1	10.66	11.365	56	26.0027
1	2011-01-20 01:00:00	1	0	1	1	10.66	13.635	56	0.0000
2	2011-01-20 02:00:00	1	0	1	1	10.66	13.635	56	0.0000
3	2011-01-20 03:00:00	1	0	1	1	10.66	12.880	56	11.0014
4	2011-01-20 04:00:00	1	0	1	1	10.66	12.880	56	11.0014

# Same thing as train and test dataset
submission = pd.read_csv('bike-sharing-demand/sampleSubmission.csv',parse_dates =['datetime'])
submission.head()

	datetime	count
0	2011-01-20 00:00:00	0
1	2011-01-20 01:00:00	0
2	2011-01-20 02:00:00	0
3	2011-01-20 03:00:00	0
4	2011-01-20 04:00:00	0

Step 3: Train a model using AutoGluon’s Tabular Prediction

Requirements:

• We are prediting count, so it is the label we are setting.
• Ignore casual and registered columns as they are also not present in the test dataset.
• Use the root_mean_squared_error as the metric to use for evaluation.
• Set a time limit of 10 minutes (600 seconds).
• Use the preset best_quality to focus on creating the best model.

train.head()

	datetime	season	holiday	workingday	weather	temp	atemp	humidity	windspeed	casual	registered	count
0	2011-01-01 00:00:00	1	0	0	1	9.84	14.395	81	0.0	3	13	16
1	2011-01-01 01:00:00	1	0	0	1	9.02	13.635	80	0.0	8	32	40
2	2011-01-01 02:00:00	1	0	0	1	9.02	13.635	80	0.0	5	27	32
3	2011-01-01 03:00:00	1	0	0	1	9.84	14.395	75	0.0	3	10	13
4	2011-01-01 04:00:00	1	0	0	1	9.84	14.395	75	0.0	0	1	1

predictor = TabularPredictor('count',problem_type='regression',learner_kwargs={"ignored_columns":['casual','registered']},
                             eval_metric='root_mean_squared_error').fit(train,time_limit=600,presets='best_quality')

No path specified. Models will be saved in: "AutogluonModels\ag-20230531_013647\"
Presets specified: ['best_quality']
Stack configuration (auto_stack=True): num_stack_levels=1, num_bag_folds=8, num_bag_sets=20
Beginning AutoGluon training ... Time limit = 600s
AutoGluon will save models to "AutogluonModels\ag-20230531_013647\"
AutoGluon Version:  0.7.0
Python Version:     3.8.16
Operating System:   Windows
Platform Machine:   AMD64
Platform Version:   10.0.19045
Train Data Rows:    10886
Train Data Columns: 11
Label Column: count
Preprocessing data ...
Using Feature Generators to preprocess the data ...
Dropping user-specified ignored columns: ['casual', 'registered']
Fitting AutoMLPipelineFeatureGenerator...
	Available Memory:                    7862.13 MB
	Train Data (Original)  Memory Usage: 0.78 MB (0.0% of available memory)
	Inferring data type of each feature based on column values. Set feature_metadata_in to manually specify special dtypes of the features.
	Stage 1 Generators:
		Fitting AsTypeFeatureGenerator...
			Note: Converting 2 features to boolean dtype as they only contain 2 unique values.
	Stage 2 Generators:
		Fitting FillNaFeatureGenerator...
	Stage 3 Generators:
		Fitting IdentityFeatureGenerator...
		Fitting DatetimeFeatureGenerator...
	Stage 4 Generators:
		Fitting DropUniqueFeatureGenerator...
	Types of features in original data (raw dtype, special dtypes):
		('datetime', []) : 1 | ['datetime']
		('float', [])    : 3 | ['temp', 'atemp', 'windspeed']
		('int', [])      : 5 | ['season', 'holiday', 'workingday', 'weather', 'humidity']
	Types of features in processed data (raw dtype, special dtypes):
		('float', [])                : 3 | ['temp', 'atemp', 'windspeed']
		('int', [])                  : 3 | ['season', 'weather', 'humidity']
		('int', ['bool'])            : 2 | ['holiday', 'workingday']
		('int', ['datetime_as_int']) : 5 | ['datetime', 'datetime.year', 'datetime.month', 'datetime.day', 'datetime.dayofweek']
	0.1s = Fit runtime
	9 features in original data used to generate 13 features in processed data.
	Train Data (Processed) Memory Usage: 0.98 MB (0.0% of available memory)
Data preprocessing and feature engineering runtime = 0.1s ...
AutoGluon will gauge predictive performance using evaluation metric: 'root_mean_squared_error'
	This metric's sign has been flipped to adhere to being higher_is_better. The metric score can be multiplied by -1 to get the metric value.
	To change this, specify the eval_metric parameter of Predictor()
AutoGluon will fit 2 stack levels (L1 to L2) ...
Fitting 11 L1 models ...
Fitting model: KNeighborsUnif_BAG_L1 ... Training model for up to 399.83s of the 599.9s of remaining time.
	-101.5882	 = Validation score   (-root_mean_squared_error)
	0.05s	 = Training   runtime
	0.02s	 = Validation runtime
Fitting model: KNeighborsDist_BAG_L1 ... Training model for up to 399.71s of the 599.78s of remaining time.
	-84.1464	 = Validation score   (-root_mean_squared_error)
	0.05s	 = Training   runtime
	0.03s	 = Validation runtime
Fitting model: LightGBMXT_BAG_L1 ... Training model for up to 399.6s of the 599.67s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-131.4609	 = Validation score   (-root_mean_squared_error)
	16.12s	 = Training   runtime
	6.0s	 = Validation runtime
Fitting model: LightGBM_BAG_L1 ... Training model for up to 372.34s of the 572.41s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-131.0542	 = Validation score   (-root_mean_squared_error)
	5.04s	 = Training   runtime
	0.9s	 = Validation runtime
Fitting model: RandomForestMSE_BAG_L1 ... Training model for up to 357.84s of the 557.91s of remaining time.
	-116.5521	 = Validation score   (-root_mean_squared_error)
	3.51s	 = Training   runtime
	0.4s	 = Validation runtime
Fitting model: CatBoost_BAG_L1 ... Training model for up to 353.64s of the 553.71s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-130.4612	 = Validation score   (-root_mean_squared_error)
	134.11s	 = Training   runtime
	0.06s	 = Validation runtime
Fitting model: ExtraTreesMSE_BAG_L1 ... Training model for up to 210.48s of the 410.55s of remaining time.
	-124.6023	 = Validation score   (-root_mean_squared_error)
	1.31s	 = Training   runtime
	0.38s	 = Validation runtime
Fitting model: NeuralNetFastAI_BAG_L1 ... Training model for up to 208.49s of the 408.56s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-135.8377	 = Validation score   (-root_mean_squared_error)
	20.38s	 = Training   runtime
	0.21s	 = Validation runtime
Fitting model: XGBoost_BAG_L1 ... Training model for up to 179.61s of the 379.67s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-131.6247	 = Validation score   (-root_mean_squared_error)
	4.23s	 = Training   runtime
	0.32s	 = Validation runtime
Fitting model: NeuralNetTorch_BAG_L1 ... Training model for up to 165.98s of the 366.05s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-137.6134	 = Validation score   (-root_mean_squared_error)
	99.5s	 = Training   runtime
	0.11s	 = Validation runtime
Fitting model: LightGBMLarge_BAG_L1 ... Training model for up to 57.96s of the 258.03s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-130.1323	 = Validation score   (-root_mean_squared_error)
	4.88s	 = Training   runtime
	0.53s	 = Validation runtime
Completed 1/20 k-fold bagging repeats ...
Fitting model: WeightedEnsemble_L2 ... Training model for up to 359.98s of the 244.09s of remaining time.
	-84.1464	 = Validation score   (-root_mean_squared_error)
	0.61s	 = Training   runtime
	0.02s	 = Validation runtime
Fitting 9 L2 models ...
Fitting model: LightGBMXT_BAG_L2 ... Training model for up to 243.44s of the 243.42s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-60.3213	 = Validation score   (-root_mean_squared_error)
	11.38s	 = Training   runtime
	2.87s	 = Validation runtime
Fitting model: LightGBM_BAG_L2 ... Training model for up to 222.42s of the 222.39s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-55.077	 = Validation score   (-root_mean_squared_error)
	3.59s	 = Training   runtime
	0.23s	 = Validation runtime
Fitting model: RandomForestMSE_BAG_L2 ... Training model for up to 209.32s of the 209.3s of remaining time.
	-53.3799	 = Validation score   (-root_mean_squared_error)
	11.79s	 = Training   runtime
	0.48s	 = Validation runtime
Fitting model: CatBoost_BAG_L2 ... Training model for up to 196.73s of the 196.72s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-55.5555	 = Validation score   (-root_mean_squared_error)
	28.35s	 = Training   runtime
	0.05s	 = Validation runtime
Fitting model: ExtraTreesMSE_BAG_L2 ... Training model for up to 159.62s of the 159.61s of remaining time.
	-54.3037	 = Validation score   (-root_mean_squared_error)
	2.7s	 = Training   runtime
	0.42s	 = Validation runtime
Fitting model: NeuralNetFastAI_BAG_L2 ... Training model for up to 156.22s of the 156.19s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-51.7163	 = Validation score   (-root_mean_squared_error)
	21.07s	 = Training   runtime
	0.24s	 = Validation runtime
Fitting model: XGBoost_BAG_L2 ... Training model for up to 126.3s of the 126.29s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-54.9604	 = Validation score   (-root_mean_squared_error)
	4.01s	 = Training   runtime
	0.11s	 = Validation runtime
Fitting model: NeuralNetTorch_BAG_L2 ... Training model for up to 112.81s of the 112.8s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-55.1251	 = Validation score   (-root_mean_squared_error)
	77.48s	 = Training   runtime
	0.19s	 = Validation runtime
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 26.22s of the 26.2s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-55.0695	 = Validation score   (-root_mean_squared_error)
	6.94s	 = Training   runtime
	0.23s	 = Validation runtime
Completed 1/20 k-fold bagging repeats ...
Fitting model: WeightedEnsemble_L3 ... Training model for up to 360.0s of the 9.98s of remaining time.
	-50.5274	 = Validation score   (-root_mean_squared_error)
	0.48s	 = Training   runtime
	0.0s	 = Validation runtime
AutoGluon training complete, total runtime = 590.54s ... Best model: "WeightedEnsemble_L3"
TabularPredictor saved. To load, use: predictor = TabularPredictor.load("AutogluonModels\ag-20230531_013647\")

Review AutoGluon's training run with ranking of models that did the best.

predictor.fit_summary()

*** Summary of fit() ***
Estimated performance of each model:
                     model   score_val  pred_time_val    fit_time  pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  fit_order
0      WeightedEnsemble_L3  -50.545607      11.096767  409.280485                0.000000           0.361998            3       True         22
1   NeuralNetFastAI_BAG_L2  -51.716262      10.008647  322.826800                0.270120          22.167076            2       True         18
2   RandomForestMSE_BAG_L2  -53.379886      10.171751  314.397344                0.433223          13.737620            2       True         15
3     ExtraTreesMSE_BAG_L2  -54.303663      10.179574  303.527697                0.441046           2.867972            2       True         17
4           XGBoost_BAG_L2  -54.960386       9.838179  304.831909                0.099651           4.172185            2       True         19
5     LightGBMLarge_BAG_L2  -55.069468      10.038877  305.921805                0.300349           5.262080            2       True         21
6          LightGBM_BAG_L2  -55.077004       9.937626  304.271100                0.199099           3.611376            2       True         14
7    NeuralNetTorch_BAG_L2  -55.314134       9.952379  370.145819                0.213851          69.486095            2       True         20
8          CatBoost_BAG_L2  -55.555501       9.775106  330.275181                0.036578          29.615457            2       True         16
9        LightGBMXT_BAG_L2  -60.321306      13.522628  313.045133                3.784101          12.385408            2       True         13
10     WeightedEnsemble_L2  -84.146423       0.021363    0.562025                0.000000           0.503019            2       True         12
11   KNeighborsDist_BAG_L1  -84.146423       0.021363    0.059006                0.021363           0.059006            1       True          2
12   KNeighborsUnif_BAG_L1 -101.588176       0.023003    0.055419                0.023003           0.055419            1       True          1
13  RandomForestMSE_BAG_L1 -116.552091       0.380218    3.619674                0.380218           3.619674            1       True          5
14    ExtraTreesMSE_BAG_L1 -124.602302       0.371037    1.416224                0.371037           1.416224            1       True          7
15    LightGBMLarge_BAG_L1 -130.132290       0.633200    5.427717                0.633200           5.427717            1       True         11
16         CatBoost_BAG_L1 -130.461205       0.052495  139.030226                0.052495         139.030226            1       True          6
17         LightGBM_BAG_L1 -131.054162       0.934174    5.051711                0.934174           5.051711            1       True          4
18       LightGBMXT_BAG_L1 -131.460909       6.613437   16.065701                6.613437          16.065701            1       True          3
19          XGBoost_BAG_L1 -131.624665       0.349599    4.290946                0.349599           4.290946            1       True          9
20  NeuralNetFastAI_BAG_L1 -135.837680       0.237846   21.203035                0.237846          21.203035            1       True          8
21   NeuralNetTorch_BAG_L1 -137.613441       0.122154  104.440064                0.122154         104.440064            1       True         10
Number of models trained: 22
Types of models trained:
{'StackerEnsembleModel_LGB', 'StackerEnsembleModel_CatBoost', 'StackerEnsembleModel_NNFastAiTabular', 'StackerEnsembleModel_XT', 'StackerEnsembleModel_RF', 'WeightedEnsembleModel', 'StackerEnsembleModel_TabularNeuralNetTorch', 'StackerEnsembleModel_KNN', 'StackerEnsembleModel_XGBoost'}
Bagging used: True  (with 8 folds)
Multi-layer stack-ensembling used: True  (with 3 levels)
Feature Metadata (Processed):
(raw dtype, special dtypes):
('float', [])                : 3 | ['temp', 'atemp', 'windspeed']
('int', [])                  : 3 | ['season', 'weather', 'humidity']
('int', ['bool'])            : 2 | ['holiday', 'workingday']
('int', ['datetime_as_int']) : 5 | ['datetime', 'datetime.year', 'datetime.month', 'datetime.day', 'datetime.dayofweek']
*** End of fit() summary ***

C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\plots.py:138: UserWarning: AutoGluon summary plots cannot be created because bokeh is not installed. To see plots, please do: "pip install bokeh==2.0.1"
  warnings.warn('AutoGluon summary plots cannot be created because bokeh is not installed. To see plots, please do: "pip install bokeh==2.0.1"')

{'model_types': {'KNeighborsUnif_BAG_L1': 'StackerEnsembleModel_KNN',
  'KNeighborsDist_BAG_L1': 'StackerEnsembleModel_KNN',
  'LightGBMXT_BAG_L1': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1': 'StackerEnsembleModel_LGB',
  'RandomForestMSE_BAG_L1': 'StackerEnsembleModel_RF',
  'CatBoost_BAG_L1': 'StackerEnsembleModel_CatBoost',
  'ExtraTreesMSE_BAG_L1': 'StackerEnsembleModel_XT',
  'NeuralNetFastAI_BAG_L1': 'StackerEnsembleModel_NNFastAiTabular',
  'XGBoost_BAG_L1': 'StackerEnsembleModel_XGBoost',
  'NeuralNetTorch_BAG_L1': 'StackerEnsembleModel_TabularNeuralNetTorch',
  'LightGBMLarge_BAG_L1': 'StackerEnsembleModel_LGB',
  'WeightedEnsemble_L2': 'WeightedEnsembleModel',
  'LightGBMXT_BAG_L2': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2': 'StackerEnsembleModel_LGB',
  'RandomForestMSE_BAG_L2': 'StackerEnsembleModel_RF',
  'CatBoost_BAG_L2': 'StackerEnsembleModel_CatBoost',
  'ExtraTreesMSE_BAG_L2': 'StackerEnsembleModel_XT',
  'NeuralNetFastAI_BAG_L2': 'StackerEnsembleModel_NNFastAiTabular',
  'XGBoost_BAG_L2': 'StackerEnsembleModel_XGBoost',
  'NeuralNetTorch_BAG_L2': 'StackerEnsembleModel_TabularNeuralNetTorch',
  'LightGBMLarge_BAG_L2': 'StackerEnsembleModel_LGB',
  'WeightedEnsemble_L3': 'WeightedEnsembleModel'},
 'model_performance': {'KNeighborsUnif_BAG_L1': -101.58817625927213,
  'KNeighborsDist_BAG_L1': -84.14642264302962,
  'LightGBMXT_BAG_L1': -131.46090891834504,
  'LightGBM_BAG_L1': -131.054161598899,
  'RandomForestMSE_BAG_L1': -116.55209143577434,
  'CatBoost_BAG_L1': -130.46120460893414,
  'ExtraTreesMSE_BAG_L1': -124.60230209225125,
  'NeuralNetFastAI_BAG_L1': -135.83768030668705,
  'XGBoost_BAG_L1': -131.62466543942023,
  'NeuralNetTorch_BAG_L1': -137.61344101796504,
  'LightGBMLarge_BAG_L1': -130.13228993716103,
  'WeightedEnsemble_L2': -84.14642264302962,
  'LightGBMXT_BAG_L2': -60.32130645032012,
  'LightGBM_BAG_L2': -55.07700383080456,
  'RandomForestMSE_BAG_L2': -53.37988550271052,
  'CatBoost_BAG_L2': -55.55550138438511,
  'ExtraTreesMSE_BAG_L2': -54.30366322835222,
  'NeuralNetFastAI_BAG_L2': -51.71626228633236,
  'XGBoost_BAG_L2': -54.96038583691514,
  'NeuralNetTorch_BAG_L2': -55.31413429144492,
  'LightGBMLarge_BAG_L2': -55.06946824246353,
  'WeightedEnsemble_L3': -50.54560736437441},
 'model_best': 'WeightedEnsemble_L3',
 'model_paths': {'KNeighborsUnif_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\KNeighborsUnif_BAG_L1\\',
  'KNeighborsDist_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\KNeighborsDist_BAG_L1\\',
  'LightGBMXT_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\LightGBMXT_BAG_L1\\',
  'LightGBM_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\LightGBM_BAG_L1\\',
  'RandomForestMSE_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\RandomForestMSE_BAG_L1\\',
  'CatBoost_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\CatBoost_BAG_L1\\',
  'ExtraTreesMSE_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\ExtraTreesMSE_BAG_L1\\',
  'NeuralNetFastAI_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\NeuralNetFastAI_BAG_L1\\',
  'XGBoost_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\XGBoost_BAG_L1\\',
  'NeuralNetTorch_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\NeuralNetTorch_BAG_L1\\',
  'LightGBMLarge_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\LightGBMLarge_BAG_L1\\',
  'WeightedEnsemble_L2': 'AutogluonModels\\ag-20230530_052724\\models\\WeightedEnsemble_L2\\',
  'LightGBMXT_BAG_L2': 'AutogluonModels\\ag-20230530_052724\\models\\LightGBMXT_BAG_L2\\',
  'LightGBM_BAG_L2': 'AutogluonModels\\ag-20230530_052724\\models\\LightGBM_BAG_L2\\',
  'RandomForestMSE_BAG_L2': 'AutogluonModels\\ag-20230530_052724\\models\\RandomForestMSE_BAG_L2\\',
  'CatBoost_BAG_L2': 'AutogluonModels\\ag-20230530_052724\\models\\CatBoost_BAG_L2\\',
  'ExtraTreesMSE_BAG_L2': 'AutogluonModels\\ag-20230530_052724\\models\\ExtraTreesMSE_BAG_L2\\',
  'NeuralNetFastAI_BAG_L2': 'AutogluonModels\\ag-20230530_052724\\models\\NeuralNetFastAI_BAG_L2\\',
  'XGBoost_BAG_L2': 'AutogluonModels\\ag-20230530_052724\\models\\XGBoost_BAG_L2\\',
  'NeuralNetTorch_BAG_L2': 'AutogluonModels\\ag-20230530_052724\\models\\NeuralNetTorch_BAG_L2\\',
  'LightGBMLarge_BAG_L2': 'AutogluonModels\\ag-20230530_052724\\models\\LightGBMLarge_BAG_L2\\',
  'WeightedEnsemble_L3': 'AutogluonModels\\ag-20230530_052724\\models\\WeightedEnsemble_L3\\'},
 'model_fit_times': {'KNeighborsUnif_BAG_L1': 0.0554194450378418,
  'KNeighborsDist_BAG_L1': 0.0590062141418457,
  'LightGBMXT_BAG_L1': 16.065701246261597,
  'LightGBM_BAG_L1': 5.051711320877075,
  'RandomForestMSE_BAG_L1': 3.619673728942871,
  'CatBoost_BAG_L1': 139.03022646903992,
  'ExtraTreesMSE_BAG_L1': 1.4162240028381348,
  'NeuralNetFastAI_BAG_L1': 21.2030348777771,
  'XGBoost_BAG_L1': 4.290945768356323,
  'NeuralNetTorch_BAG_L1': 104.44006395339966,
  'LightGBMLarge_BAG_L1': 5.427717447280884,
  'WeightedEnsemble_L2': 0.5030190944671631,
  'LightGBMXT_BAG_L2': 12.385408163070679,
  'LightGBM_BAG_L2': 3.6113758087158203,
  'RandomForestMSE_BAG_L2': 13.737619876861572,
  'CatBoost_BAG_L2': 29.6154568195343,
  'ExtraTreesMSE_BAG_L2': 2.8679721355438232,
  'NeuralNetFastAI_BAG_L2': 22.167075872421265,
  'XGBoost_BAG_L2': 4.172184705734253,
  'NeuralNetTorch_BAG_L2': 69.48609471321106,
  'LightGBMLarge_BAG_L2': 5.262080192565918,
  'WeightedEnsemble_L3': 0.3619976043701172},
 'model_pred_times': {'KNeighborsUnif_BAG_L1': 0.023003101348876953,
  'KNeighborsDist_BAG_L1': 0.021363496780395508,
  'LightGBMXT_BAG_L1': 6.613437175750732,
  'LightGBM_BAG_L1': 0.9341740608215332,
  'RandomForestMSE_BAG_L1': 0.3802177906036377,
  'CatBoost_BAG_L1': 0.05249500274658203,
  'ExtraTreesMSE_BAG_L1': 0.37103724479675293,
  'NeuralNetFastAI_BAG_L1': 0.23784637451171875,
  'XGBoost_BAG_L1': 0.34959936141967773,
  'NeuralNetTorch_BAG_L1': 0.12215352058410645,
  'LightGBMLarge_BAG_L1': 0.6332004070281982,
  'WeightedEnsemble_L2': 0.0,
  'LightGBMXT_BAG_L2': 3.7841007709503174,
  'LightGBM_BAG_L2': 0.19909882545471191,
  'RandomForestMSE_BAG_L2': 0.43322300910949707,
  'CatBoost_BAG_L2': 0.03657817840576172,
  'ExtraTreesMSE_BAG_L2': 0.44104623794555664,
  'NeuralNetFastAI_BAG_L2': 0.27011966705322266,
  'XGBoost_BAG_L2': 0.09965109825134277,
  'NeuralNetTorch_BAG_L2': 0.2138509750366211,
  'LightGBMLarge_BAG_L2': 0.30034899711608887,
  'WeightedEnsemble_L3': 0.0},
 'num_bag_folds': 8,
 'max_stack_level': 3,
 'model_hyperparams': {'KNeighborsUnif_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'KNeighborsDist_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'LightGBMXT_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'RandomForestMSE_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'CatBoost_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'ExtraTreesMSE_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'NeuralNetFastAI_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'XGBoost_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'NeuralNetTorch_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBMLarge_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'WeightedEnsemble_L2': {'use_orig_features': False,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBMXT_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'RandomForestMSE_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'CatBoost_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'ExtraTreesMSE_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'NeuralNetFastAI_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'XGBoost_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'NeuralNetTorch_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBMLarge_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'WeightedEnsemble_L3': {'use_orig_features': False,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True}},
 'leaderboard':                      model   score_val  pred_time_val    fit_time  \
 0      WeightedEnsemble_L3  -50.545607      11.096767  409.280485   
 1   NeuralNetFastAI_BAG_L2  -51.716262      10.008647  322.826800   
 2   RandomForestMSE_BAG_L2  -53.379886      10.171751  314.397344   
 3     ExtraTreesMSE_BAG_L2  -54.303663      10.179574  303.527697   
 4           XGBoost_BAG_L2  -54.960386       9.838179  304.831909   
 5     LightGBMLarge_BAG_L2  -55.069468      10.038877  305.921805   
 6          LightGBM_BAG_L2  -55.077004       9.937626  304.271100   
 7    NeuralNetTorch_BAG_L2  -55.314134       9.952379  370.145819   
 8          CatBoost_BAG_L2  -55.555501       9.775106  330.275181   
 9        LightGBMXT_BAG_L2  -60.321306      13.522628  313.045133   
 10     WeightedEnsemble_L2  -84.146423       0.021363    0.562025   
 11   KNeighborsDist_BAG_L1  -84.146423       0.021363    0.059006   
 12   KNeighborsUnif_BAG_L1 -101.588176       0.023003    0.055419   
 13  RandomForestMSE_BAG_L1 -116.552091       0.380218    3.619674   
 14    ExtraTreesMSE_BAG_L1 -124.602302       0.371037    1.416224   
 15    LightGBMLarge_BAG_L1 -130.132290       0.633200    5.427717   
 16         CatBoost_BAG_L1 -130.461205       0.052495  139.030226   
 17         LightGBM_BAG_L1 -131.054162       0.934174    5.051711   
 18       LightGBMXT_BAG_L1 -131.460909       6.613437   16.065701   
 19          XGBoost_BAG_L1 -131.624665       0.349599    4.290946   
 20  NeuralNetFastAI_BAG_L1 -135.837680       0.237846   21.203035   
 21   NeuralNetTorch_BAG_L1 -137.613441       0.122154  104.440064   
 
     pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  \
 0                 0.000000           0.361998            3       True   
 1                 0.270120          22.167076            2       True   
 2                 0.433223          13.737620            2       True   
 3                 0.441046           2.867972            2       True   
 4                 0.099651           4.172185            2       True   
 5                 0.300349           5.262080            2       True   
 6                 0.199099           3.611376            2       True   
 7                 0.213851          69.486095            2       True   
 8                 0.036578          29.615457            2       True   
 9                 3.784101          12.385408            2       True   
 10                0.000000           0.503019            2       True   
 11                0.021363           0.059006            1       True   
 12                0.023003           0.055419            1       True   
 13                0.380218           3.619674            1       True   
 14                0.371037           1.416224            1       True   
 15                0.633200           5.427717            1       True   
 16                0.052495         139.030226            1       True   
 17                0.934174           5.051711            1       True   
 18                6.613437          16.065701            1       True   
 19                0.349599           4.290946            1       True   
 20                0.237846          21.203035            1       True   
 21                0.122154         104.440064            1       True   
 
     fit_order  
 0          22  
 1          18  
 2          15  
 3          17  
 4          19  
 5          21  
 6          14  
 7          20  
 8          16  
 9          13  
 10         12  
 11          2  
 12          1  
 13          5  
 14          7  
 15         11  
 16          6  
 17          4  
 18          3  
 19          9  
 20          8  
 21         10  }

Create predictions from test dataset

best_model_name = predictor.get_model_best()

predictions = predictor.predict(test,model=best_model_name)
predictions.head()

0    24.909117
1    39.908840
2    44.751022
3    48.349266
4    50.776348
Name: count, dtype: float32

NOTE: Kaggle will reject the submission if we don't set everything to be > 0.

# Describe the `predictions` series to see if there are any negative values
predictions.describe()

count    6493.000000
mean       99.896164
std        88.322205
min         0.362242
25%        21.798826
50%        67.599335
75%       168.456116
max       351.272461
Name: count, dtype: float64

# How many negative values do we have?
predictions[predictions<0].count()

0

# Set them to zero
predictions[predictions<0]=0

Set predictions to submission dataframe, save, and submit

submission["count"] = predictions
submission.to_csv("submission.csv", index=False)

!kaggle competitions submit -c bike-sharing-demand -f submission.csv -m "first raw submission"

Successfully submitted to Bike Sharing Demand

  0%|          | 0.00/195k [00:00<?, ?B/s]
  4%|4         | 8.00k/195k [01:24<32:49, 97.1B/s]
 94%|#########4| 184k/195k [01:24<00:03, 3.14kB/s]
100%|##########| 195k/195k [01:28<00:00, 2.25kB/s]

View submission via the command line or in the web browser under the competition's page - My Submissions

!kaggle competitions submissions -c bike-sharing-demand
#| tail -n +1 | head -n 6

fileName        date                 description           status    publicScore  privateScore  
--------------  -------------------  --------------------  --------  -----------  ------------  
submission.csv  2023-05-30 05:49:46  first raw submission  complete  1.80425      1.80425       

Initial score of 1.80425

Step 4: Exploratory Data Analysis and Creating an additional feature

• Any additional feature will do, but a great suggestion would be to separate out the datetime into hour, day, or month parts.

corr=train.corr()
sns.heatmap(corr,  cmap="Blues", annot=False,
        xticklabels=corr.columns,
        yticklabels=corr.columns);

# Create a histogram of all features to show the distribution of each one relative to the data. This is part of the exploritory data analysis
fig,ax=plt.subplots(figsize=[20,15]);
train.hist(edgecolor='black', grid=False,ax=ax);

train.datetime.dt.day_name()

0         Saturday
1         Saturday
2         Saturday
3         Saturday
4         Saturday
           ...    
10881    Wednesday
10882    Wednesday
10883    Wednesday
10884    Wednesday
10885    Wednesday
Name: datetime, Length: 10886, dtype: object

# create a new feature
train['year'] = train.datetime.dt.year
train['week'] = train.datetime.dt.week
train['hour'] = train.datetime.dt.hour
train['weekday'] = train.datetime.dt.day_name()
test['year'] = test.datetime.dt.year
test['week'] = test.datetime.dt.week
test['hour'] = test.datetime.dt.hour
test['weekday'] = test.datetime.dt.day_name()

Make category types for these so models know they are not just numbers

• AutoGluon originally sees these as ints, but in reality they are int representations of a category.
• Setting the dtype to category will classify these as categories in AutoGluon.

train["season"] = train["season"].astype('category')
train["weather"] = train["weather"].astype('category')
test["season"] = test["season"].astype('category')
test["weather"] = test["weather"].astype('category')

train['year'] = train["year"].astype('category')
# train['week'] = train["week"].astype('category')
# train['hour'] = train["hour"].astype('category')
train['weekday'] = train["weekday"].astype('category')
test['year'] = test["year"].astype('category')
# test['week'] = test["week"].astype('category')
# test['hour'] = test["hour"].astype('category')
test['weekday'] = test["weekday"].astype('category')

# View are new feature
train.head()

	datetime	season	holiday	workingday	weather	temp	atemp	humidity	windspeed	casual	registered	count	year	week	hour	weekday
0	2011-01-01 00:00:00	1	0	0	1	9.84	14.395	81	0.0	3	13	16	2011	52	0	Saturday
1	2011-01-01 01:00:00	1	0	0	1	9.02	13.635	80	0.0	8	32	40	2011	52	1	Saturday
2	2011-01-01 02:00:00	1	0	0	1	9.02	13.635	80	0.0	5	27	32	2011	52	2	Saturday
3	2011-01-01 03:00:00	1	0	0	1	9.84	14.395	75	0.0	3	10	13	2011	52	3	Saturday
4	2011-01-01 04:00:00	1	0	0	1	9.84	14.395	75	0.0	0	1	1	2011	52	4	Saturday

corr=train.corr()
sns.heatmap(corr,  cmap="Blues", annot=False,
        xticklabels=corr.columns,
        yticklabels=corr.columns);

# View histogram of all features again now with the hour feature
fig,ax=plt.subplots(figsize=[20,15]);
train.hist(edgecolor='black', grid=False,ax=ax);

Step 5: Rerun the model with the same settings as before, just with more features

predictor_new_features = TabularPredictor('count',problem_type='regression',learner_kwargs={"ignored_columns":['casual','registered']},
                             eval_metric='root_mean_squared_error').fit(train,time_limit=600,presets='best_quality')

No path specified. Models will be saved in: "AutogluonModels\ag-20230530_061306\"
Presets specified: ['best_quality']
Stack configuration (auto_stack=True): num_stack_levels=1, num_bag_folds=8, num_bag_sets=20
Beginning AutoGluon training ... Time limit = 600s
AutoGluon will save models to "AutogluonModels\ag-20230530_061306\"
AutoGluon Version:  0.7.0
Python Version:     3.8.16
Operating System:   Windows
Platform Machine:   AMD64
Platform Version:   10.0.19045
Train Data Rows:    10886
Train Data Columns: 15
Label Column: count
Preprocessing data ...
Using Feature Generators to preprocess the data ...
Dropping user-specified ignored columns: ['casual', 'registered']
Fitting AutoMLPipelineFeatureGenerator...
	Available Memory:                    6493.93 MB
	Train Data (Original)  Memory Usage: 1.59 MB (0.0% of available memory)
	Inferring data type of each feature based on column values. Set feature_metadata_in to manually specify special dtypes of the features.
	Stage 1 Generators:
		Fitting AsTypeFeatureGenerator...
			Note: Converting 3 features to boolean dtype as they only contain 2 unique values.
	Stage 2 Generators:
		Fitting FillNaFeatureGenerator...
	Stage 3 Generators:
		Fitting IdentityFeatureGenerator...
		Fitting CategoryFeatureGenerator...
			Fitting CategoryMemoryMinimizeFeatureGenerator...
		Fitting DatetimeFeatureGenerator...
	Stage 4 Generators:
		Fitting DropUniqueFeatureGenerator...
	Types of features in original data (raw dtype, special dtypes):
		('category', []) : 2 | ['season', 'weather']
		('datetime', []) : 1 | ['datetime']
		('float', [])    : 3 | ['temp', 'atemp', 'windspeed']
		('int', [])      : 6 | ['holiday', 'workingday', 'humidity', 'year', 'week', ...]
		('object', [])   : 1 | ['weekday']
	Types of features in processed data (raw dtype, special dtypes):
		('category', [])             : 3 | ['season', 'weather', 'weekday']
		('float', [])                : 3 | ['temp', 'atemp', 'windspeed']
		('int', [])                  : 3 | ['humidity', 'week', 'hour']
		('int', ['bool'])            : 3 | ['holiday', 'workingday', 'year']
		('int', ['datetime_as_int']) : 5 | ['datetime', 'datetime.year', 'datetime.month', 'datetime.day', 'datetime.dayofweek']
	0.1s = Fit runtime
	13 features in original data used to generate 17 features in processed data.
	Train Data (Processed) Memory Usage: 1.02 MB (0.0% of available memory)
Data preprocessing and feature engineering runtime = 0.13s ...
AutoGluon will gauge predictive performance using evaluation metric: 'root_mean_squared_error'
	This metric's sign has been flipped to adhere to being higher_is_better. The metric score can be multiplied by -1 to get the metric value.
	To change this, specify the eval_metric parameter of Predictor()
AutoGluon will fit 2 stack levels (L1 to L2) ...
Fitting 11 L1 models ...
Fitting model: KNeighborsUnif_BAG_L1 ... Training model for up to 399.81s of the 599.86s of remaining time.
	-101.5882	 = Validation score   (-root_mean_squared_error)
	0.05s	 = Training   runtime
	0.02s	 = Validation runtime
Fitting model: KNeighborsDist_BAG_L1 ... Training model for up to 399.69s of the 599.74s of remaining time.
	-84.1464	 = Validation score   (-root_mean_squared_error)
	0.06s	 = Training   runtime
	0.03s	 = Validation runtime
Fitting model: LightGBMXT_BAG_L1 ... Training model for up to 399.58s of the 599.63s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-34.0003	 = Validation score   (-root_mean_squared_error)
	23.42s	 = Training   runtime
	11.91s	 = Validation runtime
Fitting model: LightGBM_BAG_L1 ... Training model for up to 363.28s of the 563.33s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.8875	 = Validation score   (-root_mean_squared_error)
	15.95s	 = Training   runtime
	2.69s	 = Validation runtime
Fitting model: RandomForestMSE_BAG_L1 ... Training model for up to 336.91s of the 536.96s of remaining time.
	-38.2637	 = Validation score   (-root_mean_squared_error)
	3.91s	 = Training   runtime
	0.39s	 = Validation runtime
Fitting model: CatBoost_BAG_L1 ... Training model for up to 332.28s of the 532.33s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.9105	 = Validation score   (-root_mean_squared_error)
	266.12s	 = Training   runtime
	0.14s	 = Validation runtime
Fitting model: ExtraTreesMSE_BAG_L1 ... Training model for up to 57.83s of the 257.89s of remaining time.
	-37.9605	 = Validation score   (-root_mean_squared_error)
	2.37s	 = Training   runtime
	0.44s	 = Validation runtime
Fitting model: NeuralNetFastAI_BAG_L1 ... Training model for up to 54.68s of the 254.74s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-44.205	 = Validation score   (-root_mean_squared_error)
	23.72s	 = Training   runtime
	0.39s	 = Validation runtime
Fitting model: XGBoost_BAG_L1 ... Training model for up to 22.03s of the 222.09s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-34.6233	 = Validation score   (-root_mean_squared_error)
	12.38s	 = Training   runtime
	0.71s	 = Validation runtime
Completed 1/20 k-fold bagging repeats ...
Fitting model: WeightedEnsemble_L2 ... Training model for up to 360.0s of the 199.53s of remaining time.
	-31.9455	 = Validation score   (-root_mean_squared_error)
	0.4s	 = Training   runtime
	0.0s	 = Validation runtime
Fitting 9 L2 models ...
Fitting model: LightGBMXT_BAG_L2 ... Training model for up to 199.11s of the 199.1s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-31.1964	 = Validation score   (-root_mean_squared_error)
	4.94s	 = Training   runtime
	0.54s	 = Validation runtime
Fitting model: LightGBM_BAG_L2 ... Training model for up to 185.05s of the 185.04s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-30.7771	 = Validation score   (-root_mean_squared_error)
	4.03s	 = Training   runtime
	0.24s	 = Validation runtime
Fitting model: RandomForestMSE_BAG_L2 ... Training model for up to 171.53s of the 171.52s of remaining time.
	-31.8463	 = Validation score   (-root_mean_squared_error)
	12.21s	 = Training   runtime
	0.46s	 = Validation runtime
Fitting model: CatBoost_BAG_L2 ... Training model for up to 158.53s of the 158.52s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-30.4971	 = Validation score   (-root_mean_squared_error)
	126.81s	 = Training   runtime
	0.05s	 = Validation runtime
Fitting model: ExtraTreesMSE_BAG_L2 ... Training model for up to 22.93s of the 22.93s of remaining time.
	-31.6902	 = Validation score   (-root_mean_squared_error)
	2.98s	 = Training   runtime
	0.44s	 = Validation runtime
Fitting model: NeuralNetFastAI_BAG_L2 ... Training model for up to 19.22s of the 19.22s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-30.3001	 = Validation score   (-root_mean_squared_error)
	18.73s	 = Training   runtime
	0.31s	 = Validation runtime
Completed 1/20 k-fold bagging repeats ...
Fitting model: WeightedEnsemble_L3 ... Training model for up to 360.0s of the -8.14s of remaining time.
	-29.8901	 = Validation score   (-root_mean_squared_error)
	0.28s	 = Training   runtime
	0.0s	 = Validation runtime
AutoGluon training complete, total runtime = 608.44s ... Best model: "WeightedEnsemble_L3"
TabularPredictor saved. To load, use: predictor = TabularPredictor.load("AutogluonModels\ag-20230530_061306\")

predictor_new_features.fit_summary()

*** Summary of fit() ***
Estimated performance of each model:
                     model   score_val  pred_time_val    fit_time  pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  fit_order
0      WeightedEnsemble_L3  -29.890078      17.328178  497.813932                0.000000           0.277118            3       True         17
1   NeuralNetFastAI_BAG_L2  -30.300083      17.032513  366.699103                0.309780          18.725494            2       True         16
2          CatBoost_BAG_L2  -30.497057      16.777017  474.781693                0.054284         126.808084            2       True         14
3          LightGBM_BAG_L2  -30.777089      16.964114  352.003236                0.241381           4.029627            2       True         12
4        LightGBMXT_BAG_L2  -31.196428      17.262372  352.911093                0.539639           4.937484            2       True         11
5     ExtraTreesMSE_BAG_L2  -31.690163      17.162664  350.954443                0.439931           2.980835            2       True         15
6   RandomForestMSE_BAG_L2  -31.846290      17.186521  360.183255                0.463788          12.209647            2       True         13
7      WeightedEnsemble_L2  -31.945469      15.874762  322.231183                0.000000           0.399840            2       True         10
8          LightGBM_BAG_L1  -33.887545       2.687760   15.945202                2.687760          15.945202            1       True          4
9          CatBoost_BAG_L1  -33.910528       0.140069  266.118776                0.140069         266.118776            1       True          6
10       LightGBMXT_BAG_L1  -34.000297      11.907729   23.421796               11.907729          23.421796            1       True          3
11          XGBoost_BAG_L1  -34.623349       0.713807   12.375826                0.713807          12.375826            1       True          9
12    ExtraTreesMSE_BAG_L1  -37.960508       0.441126    2.371667                0.441126           2.371667            1       True          7
13  RandomForestMSE_BAG_L1  -38.263675       0.394188    3.912401                0.394188           3.912401            1       True          5
14  NeuralNetFastAI_BAG_L1  -44.205036       0.391262   23.719739                0.391262          23.719739            1       True          8
15   KNeighborsDist_BAG_L1  -84.146423       0.031208    0.057342                0.031208           0.057342            1       True          2
16   KNeighborsUnif_BAG_L1 -101.588176       0.015584    0.050859                0.015584           0.050859            1       True          1
Number of models trained: 17
Types of models trained:
{'StackerEnsembleModel_LGB', 'StackerEnsembleModel_CatBoost', 'StackerEnsembleModel_NNFastAiTabular', 'StackerEnsembleModel_XT', 'StackerEnsembleModel_RF', 'WeightedEnsembleModel', 'StackerEnsembleModel_KNN', 'StackerEnsembleModel_XGBoost'}
Bagging used: True  (with 8 folds)
Multi-layer stack-ensembling used: True  (with 3 levels)
Feature Metadata (Processed):
(raw dtype, special dtypes):
('category', [])             : 3 | ['season', 'weather', 'weekday']
('float', [])                : 3 | ['temp', 'atemp', 'windspeed']
('int', [])                  : 3 | ['humidity', 'week', 'hour']
('int', ['bool'])            : 3 | ['holiday', 'workingday', 'year']
('int', ['datetime_as_int']) : 5 | ['datetime', 'datetime.year', 'datetime.month', 'datetime.day', 'datetime.dayofweek']
*** End of fit() summary ***

{'model_types': {'KNeighborsUnif_BAG_L1': 'StackerEnsembleModel_KNN',
  'KNeighborsDist_BAG_L1': 'StackerEnsembleModel_KNN',
  'LightGBMXT_BAG_L1': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1': 'StackerEnsembleModel_LGB',
  'RandomForestMSE_BAG_L1': 'StackerEnsembleModel_RF',
  'CatBoost_BAG_L1': 'StackerEnsembleModel_CatBoost',
  'ExtraTreesMSE_BAG_L1': 'StackerEnsembleModel_XT',
  'NeuralNetFastAI_BAG_L1': 'StackerEnsembleModel_NNFastAiTabular',
  'XGBoost_BAG_L1': 'StackerEnsembleModel_XGBoost',
  'WeightedEnsemble_L2': 'WeightedEnsembleModel',
  'LightGBMXT_BAG_L2': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2': 'StackerEnsembleModel_LGB',
  'RandomForestMSE_BAG_L2': 'StackerEnsembleModel_RF',
  'CatBoost_BAG_L2': 'StackerEnsembleModel_CatBoost',
  'ExtraTreesMSE_BAG_L2': 'StackerEnsembleModel_XT',
  'NeuralNetFastAI_BAG_L2': 'StackerEnsembleModel_NNFastAiTabular',
  'WeightedEnsemble_L3': 'WeightedEnsembleModel'},
 'model_performance': {'KNeighborsUnif_BAG_L1': -101.58817625927213,
  'KNeighborsDist_BAG_L1': -84.14642264302962,
  'LightGBMXT_BAG_L1': -34.00029724644784,
  'LightGBM_BAG_L1': -33.88754549654657,
  'RandomForestMSE_BAG_L1': -38.263675022933384,
  'CatBoost_BAG_L1': -33.910528160775904,
  'ExtraTreesMSE_BAG_L1': -37.96050753822019,
  'NeuralNetFastAI_BAG_L1': -44.205036457713064,
  'XGBoost_BAG_L1': -34.623348652304394,
  'WeightedEnsemble_L2': -31.945468585211955,
  'LightGBMXT_BAG_L2': -31.1964283492438,
  'LightGBM_BAG_L2': -30.777088546205622,
  'RandomForestMSE_BAG_L2': -31.84629005491563,
  'CatBoost_BAG_L2': -30.497056547941266,
  'ExtraTreesMSE_BAG_L2': -31.6901633765071,
  'NeuralNetFastAI_BAG_L2': -30.300082951575046,
  'WeightedEnsemble_L3': -29.890077901192186},
 'model_best': 'WeightedEnsemble_L3',
 'model_paths': {'KNeighborsUnif_BAG_L1': 'AutogluonModels\\ag-20230530_061306\\models\\KNeighborsUnif_BAG_L1\\',
  'KNeighborsDist_BAG_L1': 'AutogluonModels\\ag-20230530_061306\\models\\KNeighborsDist_BAG_L1\\',
  'LightGBMXT_BAG_L1': 'AutogluonModels\\ag-20230530_061306\\models\\LightGBMXT_BAG_L1\\',
  'LightGBM_BAG_L1': 'AutogluonModels\\ag-20230530_061306\\models\\LightGBM_BAG_L1\\',
  'RandomForestMSE_BAG_L1': 'AutogluonModels\\ag-20230530_061306\\models\\RandomForestMSE_BAG_L1\\',
  'CatBoost_BAG_L1': 'AutogluonModels\\ag-20230530_061306\\models\\CatBoost_BAG_L1\\',
  'ExtraTreesMSE_BAG_L1': 'AutogluonModels\\ag-20230530_061306\\models\\ExtraTreesMSE_BAG_L1\\',
  'NeuralNetFastAI_BAG_L1': 'AutogluonModels\\ag-20230530_061306\\models\\NeuralNetFastAI_BAG_L1\\',
  'XGBoost_BAG_L1': 'AutogluonModels\\ag-20230530_061306\\models\\XGBoost_BAG_L1\\',
  'WeightedEnsemble_L2': 'AutogluonModels\\ag-20230530_061306\\models\\WeightedEnsemble_L2\\',
  'LightGBMXT_BAG_L2': 'AutogluonModels\\ag-20230530_061306\\models\\LightGBMXT_BAG_L2\\',
  'LightGBM_BAG_L2': 'AutogluonModels\\ag-20230530_061306\\models\\LightGBM_BAG_L2\\',
  'RandomForestMSE_BAG_L2': 'AutogluonModels\\ag-20230530_061306\\models\\RandomForestMSE_BAG_L2\\',
  'CatBoost_BAG_L2': 'AutogluonModels\\ag-20230530_061306\\models\\CatBoost_BAG_L2\\',
  'ExtraTreesMSE_BAG_L2': 'AutogluonModels\\ag-20230530_061306\\models\\ExtraTreesMSE_BAG_L2\\',
  'NeuralNetFastAI_BAG_L2': 'AutogluonModels\\ag-20230530_061306\\models\\NeuralNetFastAI_BAG_L2\\',
  'WeightedEnsemble_L3': 'AutogluonModels\\ag-20230530_061306\\models\\WeightedEnsemble_L3\\'},
 'model_fit_times': {'KNeighborsUnif_BAG_L1': 0.05085945129394531,
  'KNeighborsDist_BAG_L1': 0.0573420524597168,
  'LightGBMXT_BAG_L1': 23.421796083450317,
  'LightGBM_BAG_L1': 15.945202350616455,
  'RandomForestMSE_BAG_L1': 3.912400722503662,
  'CatBoost_BAG_L1': 266.118775844574,
  'ExtraTreesMSE_BAG_L1': 2.3716673851013184,
  'NeuralNetFastAI_BAG_L1': 23.719738721847534,
  'XGBoost_BAG_L1': 12.375825881958008,
  'WeightedEnsemble_L2': 0.3998401165008545,
  'LightGBMXT_BAG_L2': 4.937484264373779,
  'LightGBM_BAG_L2': 4.029627323150635,
  'RandomForestMSE_BAG_L2': 12.209646940231323,
  'CatBoost_BAG_L2': 126.80808401107788,
  'ExtraTreesMSE_BAG_L2': 2.9808349609375,
  'NeuralNetFastAI_BAG_L2': 18.725494146347046,
  'WeightedEnsemble_L3': 0.2771182060241699},
 'model_pred_times': {'KNeighborsUnif_BAG_L1': 0.015583992004394531,
  'KNeighborsDist_BAG_L1': 0.031208038330078125,
  'LightGBMXT_BAG_L1': 11.907729148864746,
  'LightGBM_BAG_L1': 2.6877601146698,
  'RandomForestMSE_BAG_L1': 0.39418792724609375,
  'CatBoost_BAG_L1': 0.14006900787353516,
  'ExtraTreesMSE_BAG_L1': 0.44112610816955566,
  'NeuralNetFastAI_BAG_L1': 0.3912618160247803,
  'XGBoost_BAG_L1': 0.7138073444366455,
  'WeightedEnsemble_L2': 0.0,
  'LightGBMXT_BAG_L2': 0.5396385192871094,
  'LightGBM_BAG_L2': 0.2413806915283203,
  'RandomForestMSE_BAG_L2': 0.4637877941131592,
  'CatBoost_BAG_L2': 0.054283857345581055,
  'ExtraTreesMSE_BAG_L2': 0.43993067741394043,
  'NeuralNetFastAI_BAG_L2': 0.30977964401245117,
  'WeightedEnsemble_L3': 0.0},
 'num_bag_folds': 8,
 'max_stack_level': 3,
 'model_hyperparams': {'KNeighborsUnif_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'KNeighborsDist_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'LightGBMXT_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'RandomForestMSE_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'CatBoost_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'ExtraTreesMSE_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'NeuralNetFastAI_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'XGBoost_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'WeightedEnsemble_L2': {'use_orig_features': False,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBMXT_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'RandomForestMSE_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'CatBoost_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'ExtraTreesMSE_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'NeuralNetFastAI_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'WeightedEnsemble_L3': {'use_orig_features': False,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True}},
 'leaderboard':                      model   score_val  pred_time_val    fit_time  \
 0      WeightedEnsemble_L3  -29.890078      17.328178  497.813932   
 1   NeuralNetFastAI_BAG_L2  -30.300083      17.032513  366.699103   
 2          CatBoost_BAG_L2  -30.497057      16.777017  474.781693   
 3          LightGBM_BAG_L2  -30.777089      16.964114  352.003236   
 4        LightGBMXT_BAG_L2  -31.196428      17.262372  352.911093   
 5     ExtraTreesMSE_BAG_L2  -31.690163      17.162664  350.954443   
 6   RandomForestMSE_BAG_L2  -31.846290      17.186521  360.183255   
 7      WeightedEnsemble_L2  -31.945469      15.874762  322.231183   
 8          LightGBM_BAG_L1  -33.887545       2.687760   15.945202   
 9          CatBoost_BAG_L1  -33.910528       0.140069  266.118776   
 10       LightGBMXT_BAG_L1  -34.000297      11.907729   23.421796   
 11          XGBoost_BAG_L1  -34.623349       0.713807   12.375826   
 12    ExtraTreesMSE_BAG_L1  -37.960508       0.441126    2.371667   
 13  RandomForestMSE_BAG_L1  -38.263675       0.394188    3.912401   
 14  NeuralNetFastAI_BAG_L1  -44.205036       0.391262   23.719739   
 15   KNeighborsDist_BAG_L1  -84.146423       0.031208    0.057342   
 16   KNeighborsUnif_BAG_L1 -101.588176       0.015584    0.050859   
 
     pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  \
 0                 0.000000           0.277118            3       True   
 1                 0.309780          18.725494            2       True   
 2                 0.054284         126.808084            2       True   
 3                 0.241381           4.029627            2       True   
 4                 0.539639           4.937484            2       True   
 5                 0.439931           2.980835            2       True   
 6                 0.463788          12.209647            2       True   
 7                 0.000000           0.399840            2       True   
 8                 2.687760          15.945202            1       True   
 9                 0.140069         266.118776            1       True   
 10               11.907729          23.421796            1       True   
 11                0.713807          12.375826            1       True   
 12                0.441126           2.371667            1       True   
 13                0.394188           3.912401            1       True   
 14                0.391262          23.719739            1       True   
 15                0.031208           0.057342            1       True   
 16                0.015584           0.050859            1       True   
 
     fit_order  
 0          17  
 1          16  
 2          14  
 3          12  
 4          11  
 5          15  
 6          13  
 7          10  
 8           4  
 9           6  
 10          3  
 11          9  
 12          7  
 13          5  
 14          8  
 15          2  
 16          1  }

predictions_new_features = predictor_new_features.predict(test,model=predictor_new_features.get_model_best())
predictions_new_features.head()

0    14.893423
1     7.717738
2     6.931653
3     7.115042
4     7.138554
Name: count, dtype: float32

# Remember to set all negative values to zero
predictions_new_features.describe()

count    6493.000000
mean      148.880478
std       124.469337
min        -0.585657
25%        54.533398
50%       119.668686
75%       207.174530
max       785.126709
Name: count, dtype: float64

predictions_new_features[predictions_new_features<0].count()

6

predictions_new_features[predictions_new_features<0]=0

submission_new_features = submission.copy(deep=True)

# Same submitting predictions
submission_new_features["count"] = predictions_new_features
submission_new_features.to_csv("submission_new_features.csv", index=False)

!kaggle competitions submit -c bike-sharing-demand -f submission_new_features.csv -m "new features"

Successfully submitted to Bike Sharing Demand

  0%|          | 0.00/194k [00:00<?, ?B/s]
  4%|4         | 8.00k/194k [01:24<32:47, 97.1B/s]
 95%|#########4| 184k/194k [01:24<00:03, 3.14kB/s]
100%|##########| 194k/194k [01:27<00:00, 2.27kB/s]

!kaggle competitions submissions -c bike-sharing-demand 
#| tail -n +1 | head -n 6

fileName                     date                 description           status    publicScore  privateScore  
---------------------------  -------------------  --------------------  --------  -----------  ------------  
submission_new_features.csv  2023-05-30 06:32:08  new features          complete  0.70588      0.70588       
submission.csv               2023-05-30 05:49:46  first raw submission  complete  1.80425      1.80425       

New Score of 0.70588

Step 6: Hyper parameter optimization

• There are many options for hyper parameter optimization.
• Options are to change the AutoGluon higher level parameters or the individual model hyperparameters.
• The hyperparameters of the models themselves that are in AutoGluon. Those need the hyperparameter and hyperparameter_tune_kwargs arguments.

time_limit = 10*60  # train various models for 10 mins
num_trials = 10  # try at most 10 different hyperparameter configurations for each type of model
search_strategy = 'auto'  #"bayes", # random # to tune hyperparameters using Bayesian optimization routine with a local scheduler

hyperparameter_tune_kwargs = {
    'num_trials': num_trials,
    'scheduler' : "ASHA", #'local', #
    'searcher': search_strategy,
}

predictor_new_hpo = TabularPredictor('count',problem_type='regression',learner_kwargs={"ignored_columns":['casual','registered']},
                             eval_metric='root_mean_squared_error').fit(train,time_limit=600,presets='best_quality',
                                                                   hyperparameter_tune_kwargs=hyperparameter_tune_kwargs)

No model was trained during hyperparameter tuning NeuralNetTorch_BAG_L2... Skipping this model.
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 29.98s of the 235.49s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.8223	 = Validation score   (-root_mean_squared_error)
	8.56s	 = Training   runtime
	0.22s	 = Validation runtime
Repeating k-fold bagging: 2/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 222.75s of the 222.74s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.5555	 = Validation score   (-root_mean_squared_error)
	12.48s	 = Training   runtime
	0.44s	 = Validation runtime
Repeating k-fold bagging: 3/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 209.52s of the 209.51s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.4301	 = Validation score   (-root_mean_squared_error)
	16.49s	 = Training   runtime
	0.68s	 = Validation runtime
Repeating k-fold bagging: 4/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 196.24s of the 196.23s of remaining time.
	Fitting 8 child models (S4F1 - S4F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3767	 = Validation score   (-root_mean_squared_error)
	20.28s	 = Training   runtime
	0.94s	 = Validation runtime
Repeating k-fold bagging: 5/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 183.23s of the 183.22s of remaining time.
	Fitting 8 child models (S5F1 - S5F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3831	 = Validation score   (-root_mean_squared_error)
	24.0s	 = Training   runtime
	1.13s	 = Validation runtime
Repeating k-fold bagging: 6/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 170.37s of the 170.36s of remaining time.
	Fitting 8 child models (S6F1 - S6F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3714	 = Validation score   (-root_mean_squared_error)
	27.88s	 = Training   runtime
	1.37s	 = Validation runtime
Repeating k-fold bagging: 7/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 157.21s of the 157.2s of remaining time.
	Fitting 8 child models (S7F1 - S7F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3516	 = Validation score   (-root_mean_squared_error)
	31.78s	 = Training   runtime
	1.59s	 = Validation runtime
Repeating k-fold bagging: 8/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 144.23s of the 144.22s of remaining time.
	Fitting 8 child models (S8F1 - S8F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3586	 = Validation score   (-root_mean_squared_error)
	35.57s	 = Training   runtime
	1.79s	 = Validation runtime
Repeating k-fold bagging: 9/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 130.74s of the 130.73s of remaining time.
	Fitting 8 child models (S9F1 - S9F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3815	 = Validation score   (-root_mean_squared_error)
	39.77s	 = Training   runtime
	2.03s	 = Validation runtime
Repeating k-fold bagging: 10/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 117.37s of the 117.36s of remaining time.
	Fitting 8 child models (S10F1 - S10F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3955	 = Validation score   (-root_mean_squared_error)
	43.75s	 = Training   runtime
	2.22s	 = Validation runtime
Repeating k-fold bagging: 11/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 104.16s of the 104.15s of remaining time.
	Fitting 8 child models (S11F1 - S11F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3799	 = Validation score   (-root_mean_squared_error)
	47.86s	 = Training   runtime
	2.45s	 = Validation runtime
Repeating k-fold bagging: 12/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 90.81s of the 90.8s of remaining time.
	Fitting 8 child models (S12F1 - S12F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.4001	 = Validation score   (-root_mean_squared_error)
	51.86s	 = Training   runtime
	2.64s	 = Validation runtime
Repeating k-fold bagging: 13/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 77.19s of the 77.18s of remaining time.
	Fitting 8 child models (S13F1 - S13F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3765	 = Validation score   (-root_mean_squared_error)
	55.88s	 = Training   runtime
	2.83s	 = Validation runtime
Repeating k-fold bagging: 14/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 63.8s of the 63.79s of remaining time.
	Fitting 8 child models (S14F1 - S14F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3778	 = Validation score   (-root_mean_squared_error)
	59.89s	 = Training   runtime
	3.05s	 = Validation runtime
Repeating k-fold bagging: 15/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 50.53s of the 50.52s of remaining time.
	Fitting 8 child models (S15F1 - S15F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3843	 = Validation score   (-root_mean_squared_error)
	63.89s	 = Training   runtime
	3.26s	 = Validation runtime
Repeating k-fold bagging: 16/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 36.86s of the 36.85s of remaining time.
	Fitting 8 child models (S16F1 - S16F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3761	 = Validation score   (-root_mean_squared_error)
	67.85s	 = Training   runtime
	3.49s	 = Validation runtime
Repeating k-fold bagging: 17/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 23.46s of the 23.45s of remaining time.
	Fitting 8 child models (S17F1 - S17F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3623	 = Validation score   (-root_mean_squared_error)
	71.98s	 = Training   runtime
	3.72s	 = Validation runtime
Completed 17/20 k-fold bagging repeats ...
Fitting model: WeightedEnsemble_L3 ... Training model for up to 360.0s of the 9.59s of remaining time.
	-33.3623	 = Validation score   (-root_mean_squared_error)
	0.0s	 = Training   runtime
	0.0s	 = Validation runtime
AutoGluon training complete, total runtime = 590.44s ... Best model: "WeightedEnsemble_L2"
TabularPredictor saved. To load, use: predictor = TabularPredictor.load("AutogluonModels\ag-20230531_004701\")

predictor_new_hpo.fit_summary()

*** Summary of fit() ***
Estimated performance of each model:
                             model  score_val  pred_time_val    fit_time  pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  fit_order
0              WeightedEnsemble_L2 -32.375607       3.666819  196.446225                0.000000           0.158715            2       True          4
1             LightGBMLarge_BAG_L1 -32.552075       3.557436   34.594732                3.557436          34.594732            1       True          3
2             LightGBMLarge_BAG_L2 -33.362305       7.653478  313.601118                3.721043          71.981003            2       True          5
3              WeightedEnsemble_L3 -33.362305       7.654464  313.603590                0.000986           0.002472            3       True          6
4   NeuralNetTorch_BAG_L1\6349b722 -45.199272       0.109383  161.692777                0.109383         161.692777            1       True          2
5  NeuralNetFastAI_BAG_L1\5aea9def -46.628290       0.265617   45.332606                0.265617          45.332606            1       True          1
Number of models trained: 6
Types of models trained:
{'WeightedEnsembleModel', 'StackerEnsembleModel_NNFastAiTabular', 'StackerEnsembleModel_TabularNeuralNetTorch', 'StackerEnsembleModel_LGB'}
Bagging used: True  (with 8 folds)
Multi-layer stack-ensembling used: True  (with 3 levels)
Feature Metadata (Processed):
(raw dtype, special dtypes):
('category', [])             : 3 | ['season', 'weather', 'weekday']
('float', [])                : 3 | ['temp', 'atemp', 'windspeed']
('int', [])                  : 3 | ['humidity', 'week', 'hour']
('int', ['bool'])            : 3 | ['holiday', 'workingday', 'year']
('int', ['datetime_as_int']) : 5 | ['datetime', 'datetime.year', 'datetime.month', 'datetime.day', 'datetime.dayofweek']
*** End of fit() summary ***

{'model_types': {'NeuralNetFastAI_BAG_L1\\5aea9def': 'StackerEnsembleModel_NNFastAiTabular',
  'NeuralNetTorch_BAG_L1\\6349b722': 'StackerEnsembleModel_TabularNeuralNetTorch',
  'LightGBMLarge_BAG_L1': 'StackerEnsembleModel_LGB',
  'WeightedEnsemble_L2': 'WeightedEnsembleModel',
  'LightGBMLarge_BAG_L2': 'StackerEnsembleModel_LGB',
  'WeightedEnsemble_L3': 'WeightedEnsembleModel'},
 'model_performance': {'NeuralNetFastAI_BAG_L1\\5aea9def': -46.6282896132067,
  'NeuralNetTorch_BAG_L1\\6349b722': -45.199272049199045,
  'LightGBMLarge_BAG_L1': -32.552074649850724,
  'WeightedEnsemble_L2': -32.37560661696187,
  'LightGBMLarge_BAG_L2': -33.3623048521261,
  'WeightedEnsemble_L3': -33.3623048521261},
 'model_best': 'WeightedEnsemble_L2',
 'model_paths': {'NeuralNetFastAI_BAG_L1\\5aea9def': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_004701\\models\\NeuralNetFastAI_BAG_L1\\5aea9def\\',
  'NeuralNetTorch_BAG_L1\\6349b722': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_004701\\models\\NeuralNetTorch_BAG_L1\\6349b722\\',
  'LightGBMLarge_BAG_L1': 'AutogluonModels\\ag-20230531_004701\\models\\LightGBMLarge_BAG_L1\\',
  'WeightedEnsemble_L2': 'AutogluonModels\\ag-20230531_004701\\models\\WeightedEnsemble_L2\\',
  'LightGBMLarge_BAG_L2': 'AutogluonModels\\ag-20230531_004701\\models\\LightGBMLarge_BAG_L2\\',
  'WeightedEnsemble_L3': 'AutogluonModels\\ag-20230531_004701\\models\\WeightedEnsemble_L3\\'},
 'model_fit_times': {'NeuralNetFastAI_BAG_L1\\5aea9def': 45.332605600357056,
  'NeuralNetTorch_BAG_L1\\6349b722': 161.69277715682983,
  'LightGBMLarge_BAG_L1': 34.5947322845459,
  'WeightedEnsemble_L2': 0.15871524810791016,
  'LightGBMLarge_BAG_L2': 71.98100304603577,
  'WeightedEnsemble_L3': 0.0024721622467041016},
 'model_pred_times': {'NeuralNetFastAI_BAG_L1\\5aea9def': 0.26561689376831055,
  'NeuralNetTorch_BAG_L1\\6349b722': 0.10938262939453125,
  'LightGBMLarge_BAG_L1': 3.557435989379883,
  'WeightedEnsemble_L2': 0.0,
  'LightGBMLarge_BAG_L2': 3.7210428714752197,
  'WeightedEnsemble_L3': 0.000985860824584961},
 'num_bag_folds': 8,
 'max_stack_level': 3,
 'model_hyperparams': {'NeuralNetFastAI_BAG_L1\\5aea9def': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'NeuralNetTorch_BAG_L1\\6349b722': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBMLarge_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'WeightedEnsemble_L2': {'use_orig_features': False,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBMLarge_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'WeightedEnsemble_L3': {'use_orig_features': False,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True}},
 'leaderboard':                              model  score_val  pred_time_val    fit_time  \
 0              WeightedEnsemble_L2 -32.375607       3.666819  196.446225   
 1             LightGBMLarge_BAG_L1 -32.552075       3.557436   34.594732   
 2             LightGBMLarge_BAG_L2 -33.362305       7.653478  313.601118   
 3              WeightedEnsemble_L3 -33.362305       7.654464  313.603590   
 4   NeuralNetTorch_BAG_L1\6349b722 -45.199272       0.109383  161.692777   
 5  NeuralNetFastAI_BAG_L1\5aea9def -46.628290       0.265617   45.332606   
 
    pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  \
 0                0.000000           0.158715            2       True   
 1                3.557436          34.594732            1       True   
 2                3.721043          71.981003            2       True   
 3                0.000986           0.002472            3       True   
 4                0.109383         161.692777            1       True   
 5                0.265617          45.332606            1       True   
 
    fit_order  
 0          4  
 1          3  
 2          5  
 3          6  
 4          2  
 5          1  }

predictions_new_features_hpo = predictor_new_hpo.predict(test,model=predictor_new_hpo.get_model_best())
predictions_new_features_hpo.head()

0    13.315242
1    -1.718998
2    -4.141519
3     0.576120
4     0.718507
Name: count, dtype: float32

# Remember to set all negative values to zero
predictions_new_features_hpo.describe()

count    6493.000000
mean      191.578339
std       172.726730
min        -6.694787
25%        45.578114
50%       150.683228
75%       284.875244
max       876.015808
Name: count, dtype: float64

predictions_new_features_hpo[predictions_new_features_hpo<0].count()

58

predictions_new_features_hpo[predictions_new_features_hpo<0]=0

submission_new_hpo = submission.copy(deep=True)

# Same submitting predictions
submission_new_hpo["count"] = predictions_new_features_hpo
submission_new_hpo.to_csv("submission_new_hpo.csv", index=False)

!kaggle competitions submit -c bike-sharing-demand -f submission_new_hpo.csv -m "new features with hyperparameters"

Successfully submitted to Bike Sharing Demand

  0%|          | 0.00/194k [00:00<?, ?B/s]
  4%|4         | 8.00k/194k [01:24<32:48, 96.9B/s]
 95%|#########4| 184k/194k [01:24<00:03, 3.13kB/s]
100%|##########| 194k/194k [01:26<00:00, 2.29kB/s]

!kaggle competitions submissions -c bike-sharing-demand 
#| tail -n +1 | head -n 6

fileName                     date                 description                        status    publicScore  privateScore  
---------------------------  -------------------  ---------------------------------  --------  -----------  ------------  
submission_new_hpo.csv       2023-05-31 00:59:18  new features with hyperparameters  complete  0.49844      0.49844       
submission_new_features.csv  2023-05-30 06:32:08  new features                       complete  0.70588      0.70588       
submission.csv               2023-05-30 05:49:46  first raw submission               complete  1.80425      1.80425       

New Score of 0.49844

nn_options = {  # specifies non-default hyperparameter values for neural network models
    'num_epochs': 10,  # number of training epochs (controls training time of NN models)
    'learning_rate': ag.space.Real(1e-3, 1e-2, default=5e-3, log=True),  # learning rate used in training (real-valued hyperparameter searched on log-scale)
    'activation': ag.space.Categorical('relu', 'softrelu', 'tanh'),  # activation function used in NN (categorical hyperparameter, default = first entry)
    'layers': ag.space.Categorical([100],[200, 100]),  # each choice for categorical hyperparameter 'layers' corresponds to list of sizes for each NN layer to use
    'dropout_prob': ag.space.Real(0.0, 0.5, default=0.1),  # dropout probability (real-valued hyperparameter)
}

gbm_options = {  # specifies non-default hyperparameter values for lightGBM gradient boosted trees
    'num_boost_round': 80,  # number of boosting rounds (controls training time of GBM models)
    'num_leaves': ag.space.Int(lower=10, upper=50, default=20),  # number of leaves in trees (integer hyperparameter)
}

hyperparameters = {  # hyperparameters of each model type
                   'GBM': gbm_options,
                   'NN_TORCH': nn_options,
                  } 

time_limit = 10*60  # train various models for ~2 min
num_trials = 10  # try at most 5 different hyperparameter configurations for each type of model
search_strategy = 'auto'  # to tune hyperparameters using Bayesian optimization routine with a local scheduler

hyperparameter_tune_kwargs = {
    'num_trials': num_trials,
    'scheduler' : 'local',
    'searcher': search_strategy,
}

predictor_new_hpo1 = TabularPredictor('count',problem_type='regression',learner_kwargs={"ignored_columns":['casual','registered']},
                             eval_metric='root_mean_squared_error').fit(train,time_limit=time_limit,presets='best_quality',
                                                                   hyperparameters=hyperparameters, hyperparameter_tune_kwargs=hyperparameter_tune_kwargs)

No path specified. Models will be saved in: "AutogluonModels\ag-20230531_025623\"
Presets specified: ['best_quality']
Warning: hyperparameter tuning is currently experimental and may cause the process to hang.
Stack configuration (auto_stack=True): num_stack_levels=1, num_bag_folds=8, num_bag_sets=20
Beginning AutoGluon training ... Time limit = 600s
AutoGluon will save models to "AutogluonModels\ag-20230531_025623\"
AutoGluon Version:  0.7.0
Python Version:     3.8.16
Operating System:   Windows
Platform Machine:   AMD64
Platform Version:   10.0.19045
Train Data Rows:    10886
Train Data Columns: 15
Label Column: count
Preprocessing data ...
Using Feature Generators to preprocess the data ...
Dropping user-specified ignored columns: ['casual', 'registered']
Fitting AutoMLPipelineFeatureGenerator...
	Available Memory:                    8304.23 MB
	Train Data (Original)  Memory Usage: 0.83 MB (0.0% of available memory)
	Inferring data type of each feature based on column values. Set feature_metadata_in to manually specify special dtypes of the features.
	Stage 1 Generators:
		Fitting AsTypeFeatureGenerator...
			Note: Converting 3 features to boolean dtype as they only contain 2 unique values.
	Stage 2 Generators:
		Fitting FillNaFeatureGenerator...
	Stage 3 Generators:
		Fitting IdentityFeatureGenerator...
		Fitting CategoryFeatureGenerator...
			Fitting CategoryMemoryMinimizeFeatureGenerator...
		Fitting DatetimeFeatureGenerator...
	Stage 4 Generators:
		Fitting DropUniqueFeatureGenerator...
	Types of features in original data (raw dtype, special dtypes):
		('category', []) : 4 | ['season', 'weather', 'year', 'weekday']
		('datetime', []) : 1 | ['datetime']
		('float', [])    : 3 | ['temp', 'atemp', 'windspeed']
		('int', [])      : 5 | ['holiday', 'workingday', 'humidity', 'week', 'hour']
	Types of features in processed data (raw dtype, special dtypes):
		('category', [])             : 3 | ['season', 'weather', 'weekday']
		('float', [])                : 3 | ['temp', 'atemp', 'windspeed']
		('int', [])                  : 3 | ['humidity', 'week', 'hour']
		('int', ['bool'])            : 3 | ['holiday', 'workingday', 'year']
		('int', ['datetime_as_int']) : 5 | ['datetime', 'datetime.year', 'datetime.month', 'datetime.day', 'datetime.dayofweek']
	0.1s = Fit runtime
	13 features in original data used to generate 17 features in processed data.
	Train Data (Processed) Memory Usage: 1.02 MB (0.0% of available memory)
Data preprocessing and feature engineering runtime = 0.12s ...
AutoGluon will gauge predictive performance using evaluation metric: 'root_mean_squared_error'
	This metric's sign has been flipped to adhere to being higher_is_better. The metric score can be multiplied by -1 to get the metric value.
	To change this, specify the eval_metric parameter of Predictor()
AutoGluon will fit 2 stack levels (L1 to L2) ...
	WARNING: "NN" model has been deprecated in v0.4.0 and renamed to "NN_MXNET". Starting in v0.6.0, specifying "NN" or "NN_MXNET" will raise an exception. Consider instead specifying "NN_TORCH".
Fitting 2 L1 models ...
Hyperparameter tuning model: LightGBM_BAG_L1 ... Tuning model for up to 179.92s of the 599.88s of remaining time.

  0%|          | 0/10 [00:00<?, ?it/s]

	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
Fitted model: LightGBM_BAG_L1\T1 ...
	-48.1213	 = Validation score   (-root_mean_squared_error)
	10.23s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T2 ...
	-48.8559	 = Validation score   (-root_mean_squared_error)
	11.31s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T3 ...
	-41.4635	 = Validation score   (-root_mean_squared_error)
	11.41s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T4 ...
	-140.4194	 = Validation score   (-root_mean_squared_error)
	11.24s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T5 ...
	-52.1338	 = Validation score   (-root_mean_squared_error)
	11.52s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T6 ...
	-123.4752	 = Validation score   (-root_mean_squared_error)
	11.35s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T7 ...
	-48.7354	 = Validation score   (-root_mean_squared_error)
	11.02s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T8 ...
	-37.9529	 = Validation score   (-root_mean_squared_error)
	11.21s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T9 ...
	-131.3383	 = Validation score   (-root_mean_squared_error)
	11.13s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T10 ...
	-39.8167	 = Validation score   (-root_mean_squared_error)
	11.27s	 = Training   runtime
	0.0s	 = Validation runtime
Hyperparameter tuning model: NeuralNetMXNet_BAG_L1 ... Tuning model for up to 179.92s of the 487.95s of remaining time.

  0%|          | 0/10 [00:00<?, ?it/s]

	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=31724, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=31724, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=31724, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=31724, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:25,251	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:25,252	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:25,252	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=35524, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=35524, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:25,252	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=30484, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=30484, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:25,252	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:25,267	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:25,273	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=11948, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=11948, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=11948, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=11948, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:35,031	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=21156, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=21156, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:35,037	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=16048, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=16048, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:35,044	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:35,052	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:35,057	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:35,058	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:35,065	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=25204, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=25204, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=25204, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=25204, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:44,077	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:44,082	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:44,087	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:44,092	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:44,096	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:44,103	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:44,106	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=34432, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=34432, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=34432, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=34432, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:53,474	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=33764, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=33764, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:53,477	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:53,481	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=18588, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=18588, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:53,481	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=26948, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=26948, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
2023-05-31 07:58:53,497	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=35148, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=35148, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:53,500	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:53,502	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=18052, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=18052, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
ray::_ray_fit() (pid=34824, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=34824, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=34824, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=34824, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:59:03,123	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:03,129	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
2023-05-31 07:59:03,146	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:03,149	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:03,155	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:03,160	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:03,165	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
ray::_ray_fit() (pid=15848, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=15848, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=15848, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=15848, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:59:11,996	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:12,005	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:12,009	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:12,014	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:12,017	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:12,021	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
2023-05-31 07:59:12,040	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
ray::_ray_fit() (pid=35588, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=35588, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=35588, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=35588, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:59:21,215	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:21,219	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:21,225	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:21,231	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:21,239	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:21,242	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:21,272	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=11756, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=11756, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=11756, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=11756, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:59:30,477	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:30,483	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:30,488	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:30,490	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:30,499	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:30,502	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:30,507	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=21964, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=21964, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=21964, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=21964, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:59:39,565	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:39,583	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:39,588	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:39,594	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:39,598	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:39,602	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:39,605	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=27000, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=27000, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=27000, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=27000, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
No model was trained during hyperparameter tuning NeuralNetMXNet_BAG_L1... Skipping this model.
Completed 1/20 k-fold bagging repeats ...
2023-05-31 07:59:48,948	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:48,948	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:48,948	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:48,963	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:48,963	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:48,963	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:48,963	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
Fitting model: WeightedEnsemble_L2 ... Training model for up to 360.0s of the 394.53s of remaining time.
	-37.5413	 = Validation score   (-root_mean_squared_error)
	0.33s	 = Training   runtime
	0.0s	 = Validation runtime
	WARNING: "NN" model has been deprecated in v0.4.0 and renamed to "NN_MXNET". Starting in v0.6.0, specifying "NN" or "NN_MXNET" will raise an exception. Consider instead specifying "NN_TORCH".
Fitting 2 L2 models ...
Hyperparameter tuning model: LightGBM_BAG_L2 ... Tuning model for up to 177.38s of the 394.17s of remaining time.

  0%|          | 0/10 [00:00<?, ?it/s]

	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
Fitted model: LightGBM_BAG_L2\T1 ...
	-37.2839	 = Validation score   (-root_mean_squared_error)
	11.08s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T2 ...
	-36.9719	 = Validation score   (-root_mean_squared_error)
	11.68s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T3 ...
	-37.0125	 = Validation score   (-root_mean_squared_error)
	11.56s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T4 ...
	-115.2035	 = Validation score   (-root_mean_squared_error)
	11.2s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T5 ...
	-38.6166	 = Validation score   (-root_mean_squared_error)
	11.37s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T6 ...
	-111.8066	 = Validation score   (-root_mean_squared_error)
	11.08s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T7 ...
	-36.9637	 = Validation score   (-root_mean_squared_error)
	11.01s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T8 ...
	-36.5962	 = Validation score   (-root_mean_squared_error)
	11.24s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T9 ...
	-103.2097	 = Validation score   (-root_mean_squared_error)
	11.07s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T10 ...
	-36.7172	 = Validation score   (-root_mean_squared_error)
	11.18s	 = Training   runtime
	0.0s	 = Validation runtime
Hyperparameter tuning model: NeuralNetMXNet_BAG_L2 ... Tuning model for up to 177.38s of the 281.45s of remaining time.

  0%|          | 0/10 [00:00<?, ?it/s]

	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=15272, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=15272, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=15272, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=15272, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:01:52,463	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=29056, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=29056, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:01:52,468	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=24748, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=24748, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:01:52,472	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=12428, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=12428, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:01:52,475	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=35860, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=35860, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:01:52,478	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:01:52,482	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:01:52,485	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=14068, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=14068, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=14068, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=14068, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:03,281	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=19004, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=19004, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:03,312	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:03,327	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:03,333	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:03,338	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:03,343	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:03,347	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=15872, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=15872, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=15872, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=15872, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:12,750	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=6252, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=6252, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:12,754	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:12,757	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:12,761	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:12,765	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:12,770	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:12,775	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=20268, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=20268, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=20268, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=20268, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:21,907	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=24276, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=24276, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:21,918	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:21,921	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:21,921	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:21,929	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:21,934	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:21,938	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=21556, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=21556, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=21556, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=21556, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:31,743	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=21244, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=21244, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:31,754	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:31,759	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:31,764	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:31,769	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:31,773	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:31,777	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=16464, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=16464, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=16464, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=16464, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:40,925	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:40,929	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=15708, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=15708, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:40,932	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:40,935	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:40,941	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:40,945	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:40,949	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=20376, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=20376, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=20376, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=20376, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:49,869	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:49,869	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:49,869	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:49,869	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:49,885	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:49,885	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:49,885	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=29528, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=29528, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=29528, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=29528, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:58,726	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:58,733	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:58,733	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:58,740	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:58,747	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:58,747	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:58,754	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=16200, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=16200, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=16200, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=16200, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:03:07,850	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:03:07,853	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:03:07,857	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:03:07,858	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=10052, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=10052, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:03:07,866	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:03:07,871	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:03:07,875	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=15076, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=15076, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=15076, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=15076, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
No model was trained during hyperparameter tuning NeuralNetMXNet_BAG_L2... Skipping this model.
Completed 1/20 k-fold bagging repeats ...
2023-05-31 08:03:17,113	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:03:17,117	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:03:17,121	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
Fitting model: WeightedEnsemble_L3 ... Training model for up to 360.0s of the 186.45s of remaining time.
2023-05-31 08:03:17,128	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:03:17,132	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:03:17,137	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:03:17,142	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	-36.4283	 = Validation score   (-root_mean_squared_error)
	0.31s	 = Training   runtime
	0.0s	 = Validation runtime
AutoGluon training complete, total runtime = 413.92s ... Best model: "WeightedEnsemble_L3"
TabularPredictor saved. To load, use: predictor = TabularPredictor.load("AutogluonModels\ag-20230531_025623\")

predictor_new_hpo1.fit_summary()

*** Summary of fit() ***
Estimated performance of each model:
                  model   score_val  pred_time_val    fit_time  pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  fit_order
0   WeightedEnsemble_L3  -36.428313       0.001001  146.086720                0.000000           0.305657            3       True         22
1    LightGBM_BAG_L2\T8  -36.596210       0.001001  122.927084                0.000000          11.239582            2       True         19
2   LightGBM_BAG_L2\T10  -36.717208       0.001001  122.865482                0.000000          11.177980            2       True         21
3    LightGBM_BAG_L2\T7  -36.963696       0.001001  122.702333                0.000000          11.014831            2       True         18
4    LightGBM_BAG_L2\T2  -36.971947       0.001001  123.363501                0.000000          11.675999            2       True         13
5    LightGBM_BAG_L2\T3  -37.012459       0.001001  123.246503                0.000000          11.559000            2       True         14
6    LightGBM_BAG_L2\T1  -37.283893       0.001001  122.771036                0.000000          11.083534            2       True         12
7   WeightedEnsemble_L2  -37.541253       0.000000   22.808565                0.000000           0.326270            2       True         11
8    LightGBM_BAG_L1\T8  -37.952891       0.000000   11.213756                0.000000          11.213756            1       True          8
9    LightGBM_BAG_L2\T5  -38.616601       0.001001  123.054728                0.000000          11.367225            2       True         16
10  LightGBM_BAG_L1\T10  -39.816719       0.000000   11.268540                0.000000          11.268540            1       True         10
11   LightGBM_BAG_L1\T3  -41.463544       0.000000   11.409003                0.000000          11.409003            1       True          3
12   LightGBM_BAG_L1\T1  -48.121313       0.000000   10.226465                0.000000          10.226465            1       True          1
13   LightGBM_BAG_L1\T7  -48.735404       0.000000   11.016189                0.000000          11.016189            1       True          7
14   LightGBM_BAG_L1\T2  -48.855901       0.000000   11.310180                0.000000          11.310180            1       True          2
15   LightGBM_BAG_L1\T5  -52.133844       0.000000   11.518472                0.000000          11.518472            1       True          5
16   LightGBM_BAG_L2\T9 -103.209737       0.001001  122.754920                0.000000          11.067417            2       True         20
17   LightGBM_BAG_L2\T6 -111.806629       0.001001  122.767490                0.000000          11.079988            2       True         17
18   LightGBM_BAG_L2\T4 -115.203453       0.001001  122.883715                0.000000          11.196213            2       True         15
19   LightGBM_BAG_L1\T6 -123.475210       0.000000   11.351787                0.000000          11.351787            1       True          6
20   LightGBM_BAG_L1\T9 -131.338336       0.000000   11.133766                0.000000          11.133766            1       True          9
21   LightGBM_BAG_L1\T4 -140.419440       0.001001   11.239344                0.001001          11.239344            1       True          4
Number of models trained: 22
Types of models trained:
{'StackerEnsembleModel_LGB', 'WeightedEnsembleModel'}
Bagging used: True  (with 8 folds)
Multi-layer stack-ensembling used: True  (with 3 levels)
Feature Metadata (Processed):
(raw dtype, special dtypes):
('category', [])             : 3 | ['season', 'weather', 'weekday']
('float', [])                : 3 | ['temp', 'atemp', 'windspeed']
('int', [])                  : 3 | ['humidity', 'week', 'hour']
('int', ['bool'])            : 3 | ['holiday', 'workingday', 'year']
('int', ['datetime_as_int']) : 5 | ['datetime', 'datetime.year', 'datetime.month', 'datetime.day', 'datetime.dayofweek']
*** End of fit() summary ***

{'model_types': {'LightGBM_BAG_L1\\T1': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T2': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T3': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T4': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T5': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T6': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T7': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T8': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T9': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T10': 'StackerEnsembleModel_LGB',
  'WeightedEnsemble_L2': 'WeightedEnsembleModel',
  'LightGBM_BAG_L2\\T1': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T2': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T3': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T4': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T5': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T6': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T7': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T8': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T9': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T10': 'StackerEnsembleModel_LGB',
  'WeightedEnsemble_L3': 'WeightedEnsembleModel'},
 'model_performance': {'LightGBM_BAG_L1\\T1': -48.12131286915449,
  'LightGBM_BAG_L1\\T2': -48.85590120876569,
  'LightGBM_BAG_L1\\T3': -41.46354388112384,
  'LightGBM_BAG_L1\\T4': -140.41943976016316,
  'LightGBM_BAG_L1\\T5': -52.13384437355743,
  'LightGBM_BAG_L1\\T6': -123.47521008865463,
  'LightGBM_BAG_L1\\T7': -48.735403708143814,
  'LightGBM_BAG_L1\\T8': -37.95289071380219,
  'LightGBM_BAG_L1\\T9': -131.3383358294307,
  'LightGBM_BAG_L1\\T10': -39.816719373139044,
  'WeightedEnsemble_L2': -37.541252816500524,
  'LightGBM_BAG_L2\\T1': -37.28389313469878,
  'LightGBM_BAG_L2\\T2': -36.97194684554864,
  'LightGBM_BAG_L2\\T3': -37.01245930973991,
  'LightGBM_BAG_L2\\T4': -115.20345324732774,
  'LightGBM_BAG_L2\\T5': -38.616601100504866,
  'LightGBM_BAG_L2\\T6': -111.80662861630574,
  'LightGBM_BAG_L2\\T7': -36.9636959240076,
  'LightGBM_BAG_L2\\T8': -36.59621044633373,
  'LightGBM_BAG_L2\\T9': -103.20973745528875,
  'LightGBM_BAG_L2\\T10': -36.71720837197882,
  'WeightedEnsemble_L3': -36.42831329448963},
 'model_best': 'WeightedEnsemble_L3',
 'model_paths': {'LightGBM_BAG_L1\\T1': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L1\\T1\\',
  'LightGBM_BAG_L1\\T2': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L1\\T2\\',
  'LightGBM_BAG_L1\\T3': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L1\\T3\\',
  'LightGBM_BAG_L1\\T4': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L1\\T4\\',
  'LightGBM_BAG_L1\\T5': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L1\\T5\\',
  'LightGBM_BAG_L1\\T6': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L1\\T6\\',
  'LightGBM_BAG_L1\\T7': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L1\\T7\\',
  'LightGBM_BAG_L1\\T8': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L1\\T8\\',
  'LightGBM_BAG_L1\\T9': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L1\\T9\\',
  'LightGBM_BAG_L1\\T10': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L1\\T10\\',
  'WeightedEnsemble_L2': 'AutogluonModels\\ag-20230531_025623\\models\\WeightedEnsemble_L2\\',
  'LightGBM_BAG_L2\\T1': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L2\\T1\\',
  'LightGBM_BAG_L2\\T2': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L2\\T2\\',
  'LightGBM_BAG_L2\\T3': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L2\\T3\\',
  'LightGBM_BAG_L2\\T4': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L2\\T4\\',
  'LightGBM_BAG_L2\\T5': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L2\\T5\\',
  'LightGBM_BAG_L2\\T6': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L2\\T6\\',
  'LightGBM_BAG_L2\\T7': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L2\\T7\\',
  'LightGBM_BAG_L2\\T8': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L2\\T8\\',
  'LightGBM_BAG_L2\\T9': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L2\\T9\\',
  'LightGBM_BAG_L2\\T10': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L2\\T10\\',
  'WeightedEnsemble_L3': 'AutogluonModels\\ag-20230531_025623\\models\\WeightedEnsemble_L3\\'},
 'model_fit_times': {'LightGBM_BAG_L1\\T1': 10.226464986801147,
  'LightGBM_BAG_L1\\T2': 11.310179948806763,
  'LightGBM_BAG_L1\\T3': 11.409003496170044,
  'LightGBM_BAG_L1\\T4': 11.239344120025635,
  'LightGBM_BAG_L1\\T5': 11.518471717834473,
  'LightGBM_BAG_L1\\T6': 11.351787090301514,
  'LightGBM_BAG_L1\\T7': 11.016189098358154,
  'LightGBM_BAG_L1\\T8': 11.21375584602356,
  'LightGBM_BAG_L1\\T9': 11.133766412734985,
  'LightGBM_BAG_L1\\T10': 11.268539667129517,
  'WeightedEnsemble_L2': 0.32626986503601074,
  'LightGBM_BAG_L2\\T1': 11.083534002304077,
  'LightGBM_BAG_L2\\T2': 11.67599868774414,
  'LightGBM_BAG_L2\\T3': 11.559000253677368,
  'LightGBM_BAG_L2\\T4': 11.196212768554688,
  'LightGBM_BAG_L2\\T5': 11.367225170135498,
  'LightGBM_BAG_L2\\T6': 11.07998776435852,
  'LightGBM_BAG_L2\\T7': 11.014830827713013,
  'LightGBM_BAG_L2\\T8': 11.239581823348999,
  'LightGBM_BAG_L2\\T9': 11.06741738319397,
  'LightGBM_BAG_L2\\T10': 11.177979946136475,
  'WeightedEnsemble_L3': 0.30565690994262695},
 'model_pred_times': {'LightGBM_BAG_L1\\T1': 0.0,
  'LightGBM_BAG_L1\\T2': 0.0,
  'LightGBM_BAG_L1\\T3': 0.0,
  'LightGBM_BAG_L1\\T4': 0.0010008811950683594,
  'LightGBM_BAG_L1\\T5': 0.0,
  'LightGBM_BAG_L1\\T6': 0.0,
  'LightGBM_BAG_L1\\T7': 0.0,
  'LightGBM_BAG_L1\\T8': 0.0,
  'LightGBM_BAG_L1\\T9': 0.0,
  'LightGBM_BAG_L1\\T10': 0.0,
  'WeightedEnsemble_L2': 0.0,
  'LightGBM_BAG_L2\\T1': 0.0,
  'LightGBM_BAG_L2\\T2': 0.0,
  'LightGBM_BAG_L2\\T3': 0.0,
  'LightGBM_BAG_L2\\T4': 0.0,
  'LightGBM_BAG_L2\\T5': 0.0,
  'LightGBM_BAG_L2\\T6': 0.0,
  'LightGBM_BAG_L2\\T7': 0.0,
  'LightGBM_BAG_L2\\T8': 0.0,
  'LightGBM_BAG_L2\\T9': 0.0,
  'LightGBM_BAG_L2\\T10': 0.0,
  'WeightedEnsemble_L3': 0.0},
 'num_bag_folds': 8,
 'max_stack_level': 3,
 'model_hyperparams': {'LightGBM_BAG_L1\\T1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T3': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T4': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T5': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T6': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T7': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T8': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T9': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T10': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'WeightedEnsemble_L2': {'use_orig_features': False,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T3': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T4': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T5': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T6': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T7': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T8': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T9': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T10': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'WeightedEnsemble_L3': {'use_orig_features': False,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True}},
 'leaderboard':                   model   score_val  pred_time_val    fit_time  \
 0   WeightedEnsemble_L3  -36.428313       0.001001  146.086720   
 1    LightGBM_BAG_L2\T8  -36.596210       0.001001  122.927084   
 2   LightGBM_BAG_L2\T10  -36.717208       0.001001  122.865482   
 3    LightGBM_BAG_L2\T7  -36.963696       0.001001  122.702333   
 4    LightGBM_BAG_L2\T2  -36.971947       0.001001  123.363501   
 5    LightGBM_BAG_L2\T3  -37.012459       0.001001  123.246503   
 6    LightGBM_BAG_L2\T1  -37.283893       0.001001  122.771036   
 7   WeightedEnsemble_L2  -37.541253       0.000000   22.808565   
 8    LightGBM_BAG_L1\T8  -37.952891       0.000000   11.213756   
 9    LightGBM_BAG_L2\T5  -38.616601       0.001001  123.054728   
 10  LightGBM_BAG_L1\T10  -39.816719       0.000000   11.268540   
 11   LightGBM_BAG_L1\T3  -41.463544       0.000000   11.409003   
 12   LightGBM_BAG_L1\T1  -48.121313       0.000000   10.226465   
 13   LightGBM_BAG_L1\T7  -48.735404       0.000000   11.016189   
 14   LightGBM_BAG_L1\T2  -48.855901       0.000000   11.310180   
 15   LightGBM_BAG_L1\T5  -52.133844       0.000000   11.518472   
 16   LightGBM_BAG_L2\T9 -103.209737       0.001001  122.754920   
 17   LightGBM_BAG_L2\T6 -111.806629       0.001001  122.767490   
 18   LightGBM_BAG_L2\T4 -115.203453       0.001001  122.883715   
 19   LightGBM_BAG_L1\T6 -123.475210       0.000000   11.351787   
 20   LightGBM_BAG_L1\T9 -131.338336       0.000000   11.133766   
 21   LightGBM_BAG_L1\T4 -140.419440       0.001001   11.239344   
 
     pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  \
 0                 0.000000           0.305657            3       True   
 1                 0.000000          11.239582            2       True   
 2                 0.000000          11.177980            2       True   
 3                 0.000000          11.014831            2       True   
 4                 0.000000          11.675999            2       True   
 5                 0.000000          11.559000            2       True   
 6                 0.000000          11.083534            2       True   
 7                 0.000000           0.326270            2       True   
 8                 0.000000          11.213756            1       True   
 9                 0.000000          11.367225            2       True   
 10                0.000000          11.268540            1       True   
 11                0.000000          11.409003            1       True   
 12                0.000000          10.226465            1       True   
 13                0.000000          11.016189            1       True   
 14                0.000000          11.310180            1       True   
 15                0.000000          11.518472            1       True   
 16                0.000000          11.067417            2       True   
 17                0.000000          11.079988            2       True   
 18                0.000000          11.196213            2       True   
 19                0.000000          11.351787            1       True   
 20                0.000000          11.133766            1       True   
 21                0.001001          11.239344            1       True   
 
     fit_order  
 0          22  
 1          19  
 2          21  
 3          18  
 4          13  
 5          14  
 6          12  
 7          11  
 8           8  
 9          16  
 10         10  
 11          3  
 12          1  
 13          7  
 14          2  
 15          5  
 16         20  
 17         17  
 18         15  
 19          6  
 20          9  
 21          4  }

predictions_new_features_hpo1 = predictor_new_hpo1.predict(test,model=predictor_new_hpo1.get_model_best())
predictions_new_features_hpo1.describe()

count    6493.000000
mean      190.777222
std       174.822235
min         4.802301
25%        46.602318
50%       148.788101
75%       284.207275
max       875.185486
Name: count, dtype: float64

predictions_new_features_hpo1[predictions_new_features_hpo1<0].count()

0

predictions_new_features_hpo1[predictions_new_features_hpo1<0]=0

submission_new_hpo1 = submission.copy(deep=True)

# Same submitting predictions
submission_new_hpo1["count"] = predictions_new_features_hpo1
submission_new_hpo1.to_csv("submission_new_hpo1.csv", index=False)

!kaggle competitions submit -c bike-sharing-demand -f submission_new_hpo1.csv -m "new features with hyperparameters1"

Successfully submitted to Bike Sharing Demand

  0%|          | 0.00/194k [00:00<?, ?B/s]
  4%|4         | 8.00k/194k [00:00<00:05, 37.0kB/s]
 95%|#########4| 184k/194k [00:00<00:00, 726kB/s]  
100%|##########| 194k/194k [00:04<00:00, 41.4kB/s]

!kaggle competitions submissions -c bike-sharing-demand 
#| tail -n +1 | head -n 6

fileName                     date                 description                         status    publicScore  privateScore  
---------------------------  -------------------  ----------------------------------  --------  -----------  ------------  
submission_new_hpo1.csv      2023-05-31 03:08:31  new features with hyperparameters1  complete  0.46803      0.46803       
submission_new_hpo.csv       2023-05-31 01:32:59                                      complete  0.49844      0.49844       
submission_new_hpo.csv       2023-05-31 00:59:18  new features with hyperparameters   complete  0.49844      0.49844       
submission_new_features.csv  2023-05-30 06:32:08  new features                        complete  0.70588      0.70588       
submission.csv               2023-05-30 05:49:46  first raw submission                complete  1.80425      1.80425       

New Score of 0.46803

nn_options = {  # specifies non-default hyperparameter values for neural network models
    'num_epochs': ag.space.Int(lower=8, upper=20, default=10),  # number of training epochs (controls training time of NN models)
    'learning_rate': ag.space.Real(1e-3, 1e-2, default=5e-3, log=True),  # learning rate used in training (real-valued hyperparameter searched on log-scale)
    'activation': ag.space.Categorical('relu', 'softrelu', 'tanh'),  # activation function used in NN (categorical hyperparameter, default = first entry)
    'layers': ag.space.Categorical([100],[1000],[200, 100]),  # each choice for categorical hyperparameter 'layers' corresponds to list of sizes for each NN layer to use
    'dropout_prob': ag.space.Real(0.0, 0.5, default=0.1),  # dropout probability (real-valued hyperparameter)
}

gbm_options = {  # specifies non-default hyperparameter values for lightGBM gradient boosted trees
    'num_boost_round': 80,  # number of boosting rounds (controls training time of GBM models)
    'num_leaves': ag.space.Int(lower=10, upper=50, default=20),  # number of leaves in trees (integer hyperparameter)
}

hyperparameters = {  # hyperparameters of each model type
                   'GBM': gbm_options,
                   'NN_TORCH': nn_options,
                  } 

time_limit = 10*60  # train various models for ~2 min
num_trials = 10  # try at most 5 different hyperparameter configurations for each type of model
search_strategy = 'auto'  # to tune hyperparameters using Bayesian optimization routine with a local scheduler

hyperparameter_tune_kwargs = {
    'num_trials': num_trials,
    'scheduler' : 'local',
    'searcher': search_strategy,
}

predictor_new_hpo2 = TabularPredictor('count',problem_type='regression',learner_kwargs={"ignored_columns":['casual','registered']},
                             eval_metric='root_mean_squared_error').fit(train,time_limit=time_limit,presets='best_quality',
                                                               hyperparameters=hyperparameters,
                                                               hyperparameter_tune_kwargs=hyperparameter_tune_kwargs)

No path specified. Models will be saved in: "AutogluonModels\ag-20230531_043337\"
Presets specified: ['best_quality']
Warning: hyperparameter tuning is currently experimental and may cause the process to hang.
Stack configuration (auto_stack=True): num_stack_levels=1, num_bag_folds=8, num_bag_sets=20
Beginning AutoGluon training ... Time limit = 600s
AutoGluon will save models to "AutogluonModels\ag-20230531_043337\"
AutoGluon Version:  0.7.0
Python Version:     3.8.16
Operating System:   Windows
Platform Machine:   AMD64
Platform Version:   10.0.19045
Train Data Rows:    10886
Train Data Columns: 15
Label Column: count
Preprocessing data ...
Using Feature Generators to preprocess the data ...
Dropping user-specified ignored columns: ['casual', 'registered']
Fitting AutoMLPipelineFeatureGenerator...
	Available Memory:                    6915.38 MB
	Train Data (Original)  Memory Usage: 0.83 MB (0.0% of available memory)
	Inferring data type of each feature based on column values. Set feature_metadata_in to manually specify special dtypes of the features.
	Stage 1 Generators:
		Fitting AsTypeFeatureGenerator...
			Note: Converting 3 features to boolean dtype as they only contain 2 unique values.
	Stage 2 Generators:
		Fitting FillNaFeatureGenerator...
	Stage 3 Generators:
		Fitting IdentityFeatureGenerator...
		Fitting CategoryFeatureGenerator...
			Fitting CategoryMemoryMinimizeFeatureGenerator...
		Fitting DatetimeFeatureGenerator...
	Stage 4 Generators:
		Fitting DropUniqueFeatureGenerator...
	Types of features in original data (raw dtype, special dtypes):
		('category', []) : 4 | ['season', 'weather', 'year', 'weekday']
		('datetime', []) : 1 | ['datetime']
		('float', [])    : 3 | ['temp', 'atemp', 'windspeed']
		('int', [])      : 5 | ['holiday', 'workingday', 'humidity', 'week', 'hour']
	Types of features in processed data (raw dtype, special dtypes):
		('category', [])             : 3 | ['season', 'weather', 'weekday']
		('float', [])                : 3 | ['temp', 'atemp', 'windspeed']
		('int', [])                  : 3 | ['humidity', 'week', 'hour']
		('int', ['bool'])            : 3 | ['holiday', 'workingday', 'year']
		('int', ['datetime_as_int']) : 5 | ['datetime', 'datetime.year', 'datetime.month', 'datetime.day', 'datetime.dayofweek']
	0.1s = Fit runtime
	13 features in original data used to generate 17 features in processed data.
	Train Data (Processed) Memory Usage: 1.02 MB (0.0% of available memory)
Data preprocessing and feature engineering runtime = 0.17s ...
AutoGluon will gauge predictive performance using evaluation metric: 'root_mean_squared_error'
	This metric's sign has been flipped to adhere to being higher_is_better. The metric score can be multiplied by -1 to get the metric value.
	To change this, specify the eval_metric parameter of Predictor()
AutoGluon will fit 2 stack levels (L1 to L2) ...
Fitting 2 L1 models ...
Hyperparameter tuning model: LightGBM_BAG_L1 ... Tuning model for up to 179.9s of the 599.83s of remaining time.

  0%|          | 0/10 [00:00<?, ?it/s]

	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
Fitted model: LightGBM_BAG_L1\T1 ...
	-48.1213	 = Validation score   (-root_mean_squared_error)
	16.37s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T2 ...
	-48.8559	 = Validation score   (-root_mean_squared_error)
	11.35s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T3 ...
	-41.4635	 = Validation score   (-root_mean_squared_error)
	11.06s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T4 ...
	-140.4194	 = Validation score   (-root_mean_squared_error)
	10.92s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T5 ...
	-52.1338	 = Validation score   (-root_mean_squared_error)
	11.05s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T6 ...
	-123.4752	 = Validation score   (-root_mean_squared_error)
	11.05s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T7 ...
	-48.7354	 = Validation score   (-root_mean_squared_error)
	11.04s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T8 ...
	-37.9529	 = Validation score   (-root_mean_squared_error)
	10.99s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T9 ...
	-131.3383	 = Validation score   (-root_mean_squared_error)
	10.87s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T10 ...
	-39.8167	 = Validation score   (-root_mean_squared_error)
	10.85s	 = Training   runtime
	0.0s	 = Validation runtime
Hyperparameter tuning model: NeuralNetTorch_BAG_L1 ... Tuning model for up to 179.9s of the 482.89s of remaining time.
Warning: Exception caused NeuralNetTorch_BAG_L1 to fail during hyperparameter tuning... Skipping this model.
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\hyperopt\hyperopt_search.py", line 252, in _lookup
    idx = categories.index(config_dict[key])
ValueError: [100] is not in list

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\tuner.py", line 272, in fit
    return self._local_tuner.fit()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\impl\tuner_internal.py", line 420, in fit
    analysis = self._fit_internal(trainable, param_space)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\impl\tuner_internal.py", line 532, in _fit_internal
    analysis = run(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\tune.py", line 597, in run
    if config and not searcher_set_search_props(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\util.py", line 19, in _set_search_properties_backwards_compatible
    return set_search_properties_func(metric, mode, config, **spec)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\search_generator.py", line 63, in set_search_properties
    return _set_search_properties_backwards_compatible(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\util.py", line 19, in _set_search_properties_backwards_compatible
    return set_search_properties_func(metric, mode, config, **spec)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\hyperopt\hyperopt_search.py", line 292, in set_search_properties
    self._setup_hyperopt()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\hyperopt\hyperopt_search.py", line 222, in _setup_hyperopt
    self._convert_categories_to_indices(config)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\hyperopt\hyperopt_search.py", line 275, in _convert_categories_to_indices
    _lookup(config, self._space, k)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\hyperopt\hyperopt_search.py", line 271, in _lookup
    raise ValueError(msg) from exc
ValueError: Did not find category with value `[100]` in hyperopt parameter `layers`. Please make sure the specified category is valid.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\trainer\abstract_trainer.py", line 1761, in _train_single_full
    hpo_models, hpo_results = model.hyperparameter_tune(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 1257, in hyperparameter_tune
    return self._hyperparameter_tune(hpo_executor=hpo_executor, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 182, in _hyperparameter_tune
    return super()._hyperparameter_tune(X=X, y=y, k_fold=k_fold, hpo_executor=hpo_executor, preprocess_kwargs=preprocess_kwargs, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 1177, in _hyperparameter_tune
    hpo_executor.execute(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\hpo\executors.py", line 375, in execute
    analysis = run(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\hpo\ray_hpo.py", line 292, in run
    results = tuner.fit()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\tuner.py", line 274, in fit
    raise TuneError(
ray.tune.error.TuneError: The Ray Tune run failed. Please inspect the previous error messages for a cause. After fixing the issue, you can restart the run from scratch or continue this run. To continue this run, you can use `tuner = Tuner.restore("E:\online competition\kaggle\udacity_nd_bike_sharing_project\cd0385-project-starter\project\AutogluonModels\ag-20230531_043337\models\NeuralNetTorch_BAG_L1")`.
The Ray Tune run failed. Please inspect the previous error messages for a cause. After fixing the issue, you can restart the run from scratch or continue this run. To continue this run, you can use `tuner = Tuner.restore("E:\online competition\kaggle\udacity_nd_bike_sharing_project\cd0385-project-starter\project\AutogluonModels\ag-20230531_043337\models\NeuralNetTorch_BAG_L1")`.
Repeating k-fold bagging: 2/20
Fitting model: LightGBM_BAG_L1\T1 ... Training model for up to 282.4s of the 482.45s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-47.8427	 = Validation score   (-root_mean_squared_error)
	17.96s	 = Training   runtime
	0.1s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T2 ... Training model for up to 271.51s of the 471.55s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-48.4642	 = Validation score   (-root_mean_squared_error)
	12.95s	 = Training   runtime
	0.08s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T3 ... Training model for up to 260.6s of the 460.65s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-41.0288	 = Validation score   (-root_mean_squared_error)
	12.7s	 = Training   runtime
	0.11s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T4 ... Training model for up to 249.14s of the 449.19s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-140.404	 = Validation score   (-root_mean_squared_error)
	12.44s	 = Training   runtime
	0.06s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T5 ... Training model for up to 238.41s of the 438.45s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-51.9554	 = Validation score   (-root_mean_squared_error)
	12.65s	 = Training   runtime
	0.09s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T6 ... Training model for up to 227.63s of the 427.68s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-123.3835	 = Validation score   (-root_mean_squared_error)
	12.65s	 = Training   runtime
	0.08s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T7 ... Training model for up to 216.77s of the 416.82s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-48.3041	 = Validation score   (-root_mean_squared_error)
	12.58s	 = Training   runtime
	0.07s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T8 ... Training model for up to 206.06s of the 406.11s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-37.2628	 = Validation score   (-root_mean_squared_error)
	12.63s	 = Training   runtime
	0.12s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T9 ... Training model for up to 195.12s of the 395.16s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-131.3088	 = Validation score   (-root_mean_squared_error)
	12.39s	 = Training   runtime
	0.06s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T10 ... Training model for up to 184.29s of the 384.34s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-38.9148	 = Validation score   (-root_mean_squared_error)
	12.38s	 = Training   runtime
	0.09s	 = Validation runtime
Repeating k-fold bagging: 3/20
Fitting model: LightGBM_BAG_L1\T1 ... Training model for up to 173.49s of the 373.53s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-47.6504	 = Validation score   (-root_mean_squared_error)
	19.62s	 = Training   runtime
	0.21s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T2 ... Training model for up to 162.54s of the 362.59s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-48.2846	 = Validation score   (-root_mean_squared_error)
	14.51s	 = Training   runtime
	0.16s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T3 ... Training model for up to 151.71s of the 351.75s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-40.8692	 = Validation score   (-root_mean_squared_error)
	14.36s	 = Training   runtime
	0.23s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T4 ... Training model for up to 140.59s of the 340.64s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-140.3918	 = Validation score   (-root_mean_squared_error)
	13.98s	 = Training   runtime
	0.14s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T5 ... Training model for up to 129.63s of the 329.67s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-51.8047	 = Validation score   (-root_mean_squared_error)
	14.27s	 = Training   runtime
	0.17s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T6 ... Training model for up to 118.66s of the 318.7s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-123.4192	 = Validation score   (-root_mean_squared_error)
	14.31s	 = Training   runtime
	0.16s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T7 ... Training model for up to 107.79s of the 307.83s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-48.112	 = Validation score   (-root_mean_squared_error)
	14.13s	 = Training   runtime
	0.15s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T8 ... Training model for up to 96.7s of the 296.74s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-37.024	 = Validation score   (-root_mean_squared_error)
	14.23s	 = Training   runtime
	0.24s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T9 ... Training model for up to 85.84s of the 285.88s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-131.313	 = Validation score   (-root_mean_squared_error)
	14.02s	 = Training   runtime
	0.13s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T10 ... Training model for up to 74.91s of the 274.95s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-38.6076	 = Validation score   (-root_mean_squared_error)
	13.96s	 = Training   runtime
	0.18s	 = Validation runtime
Completed 3/20 k-fold bagging repeats ...
Fitting model: WeightedEnsemble_L2 ... Training model for up to 360.0s of the 263.65s of remaining time.
	-36.7956	 = Validation score   (-root_mean_squared_error)
	0.23s	 = Training   runtime
	0.0s	 = Validation runtime
Fitting 2 L2 models ...
Hyperparameter tuning model: LightGBM_BAG_L2 ... Tuning model for up to 118.53s of the 263.39s of remaining time.

  0%|          | 0/10 [00:00<?, ?it/s]

	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Stopping HPO to satisfy time limit...
Fitted model: LightGBM_BAG_L2\T1 ...
	-36.4404	 = Validation score   (-root_mean_squared_error)
	11.3s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T2 ...
	-36.172	 = Validation score   (-root_mean_squared_error)
	11.34s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T3 ...
	-36.4068	 = Validation score   (-root_mean_squared_error)
	11.44s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T4 ...
	-115.0644	 = Validation score   (-root_mean_squared_error)
	10.9s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T5 ...
	-37.7837	 = Validation score   (-root_mean_squared_error)
	11.46s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T6 ...
	-111.6776	 = Validation score   (-root_mean_squared_error)
	11.1s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T7 ...
	-36.2864	 = Validation score   (-root_mean_squared_error)
	11.29s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T8 ...
	-36.0603	 = Validation score   (-root_mean_squared_error)
	11.13s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T9 ...
	-103.007	 = Validation score   (-root_mean_squared_error)
	10.77s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T10 ...
	-35.9819	 = Validation score   (-root_mean_squared_error)
	11.11s	 = Training   runtime
	0.0s	 = Validation runtime
Hyperparameter tuning model: NeuralNetTorch_BAG_L2 ... Tuning model for up to 118.53s of the 151.32s of remaining time.
Warning: Exception caused NeuralNetTorch_BAG_L2 to fail during hyperparameter tuning... Skipping this model.
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\hyperopt\hyperopt_search.py", line 252, in _lookup
    idx = categories.index(config_dict[key])
ValueError: [100] is not in list

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\tuner.py", line 272, in fit
    return self._local_tuner.fit()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\impl\tuner_internal.py", line 420, in fit
    analysis = self._fit_internal(trainable, param_space)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\impl\tuner_internal.py", line 532, in _fit_internal
    analysis = run(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\tune.py", line 597, in run
    if config and not searcher_set_search_props(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\util.py", line 19, in _set_search_properties_backwards_compatible
    return set_search_properties_func(metric, mode, config, **spec)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\search_generator.py", line 63, in set_search_properties
    return _set_search_properties_backwards_compatible(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\util.py", line 19, in _set_search_properties_backwards_compatible
    return set_search_properties_func(metric, mode, config, **spec)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\hyperopt\hyperopt_search.py", line 292, in set_search_properties
    self._setup_hyperopt()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\hyperopt\hyperopt_search.py", line 222, in _setup_hyperopt
    self._convert_categories_to_indices(config)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\hyperopt\hyperopt_search.py", line 275, in _convert_categories_to_indices
    _lookup(config, self._space, k)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\hyperopt\hyperopt_search.py", line 271, in _lookup
    raise ValueError(msg) from exc
ValueError: Did not find category with value `[100]` in hyperopt parameter `layers`. Please make sure the specified category is valid.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\trainer\abstract_trainer.py", line 1761, in _train_single_full
    hpo_models, hpo_results = model.hyperparameter_tune(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 1257, in hyperparameter_tune
    return self._hyperparameter_tune(hpo_executor=hpo_executor, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 182, in _hyperparameter_tune
    return super()._hyperparameter_tune(X=X, y=y, k_fold=k_fold, hpo_executor=hpo_executor, preprocess_kwargs=preprocess_kwargs, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 1177, in _hyperparameter_tune
    hpo_executor.execute(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\hpo\executors.py", line 375, in execute
    analysis = run(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\hpo\ray_hpo.py", line 292, in run
    results = tuner.fit()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\tuner.py", line 274, in fit
    raise TuneError(
ray.tune.error.TuneError: The Ray Tune run failed. Please inspect the previous error messages for a cause. After fixing the issue, you can restart the run from scratch or continue this run. To continue this run, you can use `tuner = Tuner.restore("E:\online competition\kaggle\udacity_nd_bike_sharing_project\cd0385-project-starter\project\AutogluonModels\ag-20230531_043337\models\NeuralNetTorch_BAG_L2")`.
The Ray Tune run failed. Please inspect the previous error messages for a cause. After fixing the issue, you can restart the run from scratch or continue this run. To continue this run, you can use `tuner = Tuner.restore("E:\online competition\kaggle\udacity_nd_bike_sharing_project\cd0385-project-starter\project\AutogluonModels\ag-20230531_043337\models\NeuralNetTorch_BAG_L2")`.
Completed 1/20 k-fold bagging repeats ...
Fitting model: WeightedEnsemble_L3 ... Training model for up to 360.0s of the 151.22s of remaining time.
	-35.7741	 = Validation score   (-root_mean_squared_error)
	0.26s	 = Training   runtime
	0.0s	 = Validation runtime
AutoGluon training complete, total runtime = 449.07s ... Best model: "WeightedEnsemble_L3"
TabularPredictor saved. To load, use: predictor = TabularPredictor.load("AutogluonModels\ag-20230531_043337\")

predictor_new_hpo2.fit_summary()

*** Summary of fit() ***
Estimated performance of each model:
                  model   score_val  pred_time_val    fit_time  pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  fit_order
0   WeightedEnsemble_L3  -35.774051       1.772058  181.241197                0.000999           0.263998            3       True         22
1   LightGBM_BAG_L2\T10  -35.981921       1.771059  158.507892                0.001000          11.113278            2       True         21
2    LightGBM_BAG_L2\T8  -36.060335       1.770059  158.524888                0.000000          11.130274            2       True         19
3    LightGBM_BAG_L2\T2  -36.171994       1.770059  158.733648                0.000000          11.339034            2       True         13
4    LightGBM_BAG_L2\T7  -36.286430       1.770059  158.686630                0.000000          11.292016            2       True         18
5    LightGBM_BAG_L2\T3  -36.406820       1.770059  158.835299                0.000000          11.440685            2       True         14
6    LightGBM_BAG_L2\T1  -36.440448       1.770059  158.692754                0.000000          11.298140            2       True         12
7   WeightedEnsemble_L2  -36.795580       0.418004   28.422191                0.001000           0.230996            2       True         11
8    LightGBM_BAG_L1\T8  -37.024016       0.236002   14.231187                0.236002          14.231187            1       True          8
9    LightGBM_BAG_L2\T5  -37.783677       1.770059  158.849647                0.000000          11.455033            2       True         16
10  LightGBM_BAG_L1\T10  -38.607579       0.181001   13.960008                0.181001          13.960008            1       True         10
11   LightGBM_BAG_L1\T3  -40.869191       0.234013   14.358388                0.234013          14.358388            1       True          3
12   LightGBM_BAG_L1\T1  -47.650433       0.205012   19.618656                0.205012          19.618656            1       True          1
13   LightGBM_BAG_L1\T7  -48.111992       0.153008   14.131077                0.153008          14.131077            1       True          7
14   LightGBM_BAG_L1\T2  -48.284649       0.161995   14.505001                0.161995          14.505001            1       True          2
15   LightGBM_BAG_L1\T5  -51.804726       0.172031   14.274050                0.172031          14.274050            1       True          5
16   LightGBM_BAG_L2\T9 -103.007016       1.770059  158.161762                0.000000          10.767148            2       True         20
17   LightGBM_BAG_L2\T6 -111.677585       1.770059  158.498611                0.000000          11.103997            2       True         17
18   LightGBM_BAG_L2\T4 -115.064413       1.770059  158.293782                0.000000          10.899168            2       True         15
19   LightGBM_BAG_L1\T6 -123.419154       0.162997   14.314400                0.162997          14.314400            1       True          6
20   LightGBM_BAG_L1\T9 -131.312991       0.126005   14.018013                0.126005          14.018013            1       True          9
21   LightGBM_BAG_L1\T4 -140.391777       0.137994   13.983833                0.137994          13.983833            1       True          4
Number of models trained: 22
Types of models trained:
{'WeightedEnsembleModel', 'StackerEnsembleModel_LGB'}
Bagging used: True  (with 8 folds)
Multi-layer stack-ensembling used: True  (with 3 levels)
Feature Metadata (Processed):
(raw dtype, special dtypes):
('category', [])             : 3 | ['season', 'weather', 'weekday']
('float', [])                : 3 | ['temp', 'atemp', 'windspeed']
('int', [])                  : 3 | ['humidity', 'week', 'hour']
('int', ['bool'])            : 3 | ['holiday', 'workingday', 'year']
('int', ['datetime_as_int']) : 5 | ['datetime', 'datetime.year', 'datetime.month', 'datetime.day', 'datetime.dayofweek']
*** End of fit() summary ***

{'model_types': {'LightGBM_BAG_L1\\T1': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T2': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T3': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T4': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T5': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T6': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T7': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T8': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T9': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T10': 'StackerEnsembleModel_LGB',
  'WeightedEnsemble_L2': 'WeightedEnsembleModel',
  'LightGBM_BAG_L2\\T1': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T2': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T3': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T4': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T5': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T6': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T7': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T8': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T9': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T10': 'StackerEnsembleModel_LGB',
  'WeightedEnsemble_L3': 'WeightedEnsembleModel'},
 'model_performance': {'LightGBM_BAG_L1\\T1': -47.650432794522196,
  'LightGBM_BAG_L1\\T2': -48.28464931909125,
  'LightGBM_BAG_L1\\T3': -40.86919096387156,
  'LightGBM_BAG_L1\\T4': -140.39177699464057,
  'LightGBM_BAG_L1\\T5': -51.80472626835246,
  'LightGBM_BAG_L1\\T6': -123.41915363718512,
  'LightGBM_BAG_L1\\T7': -48.111991913771384,
  'LightGBM_BAG_L1\\T8': -37.02401631024006,
  'LightGBM_BAG_L1\\T9': -131.31299067162985,
  'LightGBM_BAG_L1\\T10': -38.607578808884156,
  'WeightedEnsemble_L2': -36.79558000753171,
  'LightGBM_BAG_L2\\T1': -36.440448487671716,
  'LightGBM_BAG_L2\\T2': -36.17199449477448,
  'LightGBM_BAG_L2\\T3': -36.40682028374784,
  'LightGBM_BAG_L2\\T4': -115.06441262162491,
  'LightGBM_BAG_L2\\T5': -37.78367715761663,
  'LightGBM_BAG_L2\\T6': -111.6775845548824,
  'LightGBM_BAG_L2\\T7': -36.28643017794523,
  'LightGBM_BAG_L2\\T8': -36.06033513523615,
  'LightGBM_BAG_L2\\T9': -103.00701583912745,
  'LightGBM_BAG_L2\\T10': -35.98192125320506,
  'WeightedEnsemble_L3': -35.774050913898265},
 'model_best': 'WeightedEnsemble_L3',
 'model_paths': {'LightGBM_BAG_L1\\T1': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L1\\T1\\',
  'LightGBM_BAG_L1\\T2': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L1\\T2\\',
  'LightGBM_BAG_L1\\T3': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L1\\T3\\',
  'LightGBM_BAG_L1\\T4': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L1\\T4\\',
  'LightGBM_BAG_L1\\T5': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L1\\T5\\',
  'LightGBM_BAG_L1\\T6': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L1\\T6\\',
  'LightGBM_BAG_L1\\T7': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L1\\T7\\',
  'LightGBM_BAG_L1\\T8': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L1\\T8\\',
  'LightGBM_BAG_L1\\T9': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L1\\T9\\',
  'LightGBM_BAG_L1\\T10': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L1\\T10\\',
  'WeightedEnsemble_L2': 'AutogluonModels\\ag-20230531_043337\\models\\WeightedEnsemble_L2\\',
  'LightGBM_BAG_L2\\T1': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L2\\T1\\',
  'LightGBM_BAG_L2\\T2': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L2\\T2\\',
  'LightGBM_BAG_L2\\T3': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L2\\T3\\',
  'LightGBM_BAG_L2\\T4': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L2\\T4\\',
  'LightGBM_BAG_L2\\T5': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L2\\T5\\',
  'LightGBM_BAG_L2\\T6': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L2\\T6\\',
  'LightGBM_BAG_L2\\T7': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L2\\T7\\',
  'LightGBM_BAG_L2\\T8': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L2\\T8\\',
  'LightGBM_BAG_L2\\T9': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L2\\T9\\',
  'LightGBM_BAG_L2\\T10': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L2\\T10\\',
  'WeightedEnsemble_L3': 'AutogluonModels\\ag-20230531_043337\\models\\WeightedEnsemble_L3\\'},
 'model_fit_times': {'LightGBM_BAG_L1\\T1': 19.618656158447266,
  'LightGBM_BAG_L1\\T2': 14.505001068115234,
  'LightGBM_BAG_L1\\T3': 14.358388423919678,
  'LightGBM_BAG_L1\\T4': 13.983833312988281,
  'LightGBM_BAG_L1\\T5': 14.274049997329712,
  'LightGBM_BAG_L1\\T6': 14.314399719238281,
  'LightGBM_BAG_L1\\T7': 14.131077289581299,
  'LightGBM_BAG_L1\\T8': 14.231187105178833,
  'LightGBM_BAG_L1\\T9': 14.018013000488281,
  'LightGBM_BAG_L1\\T10': 13.960007905960083,
  'WeightedEnsemble_L2': 0.23099565505981445,
  'LightGBM_BAG_L2\\T1': 11.298139810562134,
  'LightGBM_BAG_L2\\T2': 11.339033842086792,
  'LightGBM_BAG_L2\\T3': 11.44068455696106,
  'LightGBM_BAG_L2\\T4': 10.899168252944946,
  'LightGBM_BAG_L2\\T5': 11.455033302307129,
  'LightGBM_BAG_L2\\T6': 11.103997230529785,
  'LightGBM_BAG_L2\\T7': 11.292015552520752,
  'LightGBM_BAG_L2\\T8': 11.130273580551147,
  'LightGBM_BAG_L2\\T9': 10.767148494720459,
  'LightGBM_BAG_L2\\T10': 11.113278150558472,
  'WeightedEnsemble_L3': 0.26399779319763184},
 'model_pred_times': {'LightGBM_BAG_L1\\T1': 0.20501208305358887,
  'LightGBM_BAG_L1\\T2': 0.16199493408203125,
  'LightGBM_BAG_L1\\T3': 0.23401331901550293,
  'LightGBM_BAG_L1\\T4': 0.13799357414245605,
  'LightGBM_BAG_L1\\T5': 0.17203116416931152,
  'LightGBM_BAG_L1\\T6': 0.16299748420715332,
  'LightGBM_BAG_L1\\T7': 0.15300798416137695,
  'LightGBM_BAG_L1\\T8': 0.23600172996520996,
  'LightGBM_BAG_L1\\T9': 0.12600493431091309,
  'LightGBM_BAG_L1\\T10': 0.1810014247894287,
  'WeightedEnsemble_L2': 0.0010004043579101562,
  'LightGBM_BAG_L2\\T1': 0.0,
  'LightGBM_BAG_L2\\T2': 0.0,
  'LightGBM_BAG_L2\\T3': 0.0,
  'LightGBM_BAG_L2\\T4': 0.0,
  'LightGBM_BAG_L2\\T5': 0.0,
  'LightGBM_BAG_L2\\T6': 0.0,
  'LightGBM_BAG_L2\\T7': 0.0,
  'LightGBM_BAG_L2\\T8': 0.0,
  'LightGBM_BAG_L2\\T9': 0.0,
  'LightGBM_BAG_L2\\T10': 0.0010001659393310547,
  'WeightedEnsemble_L3': 0.0009989738464355469},
 'num_bag_folds': 8,
 'max_stack_level': 3,
 'model_hyperparams': {'LightGBM_BAG_L1\\T1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T3': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T4': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T5': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T6': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T7': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T8': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T9': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T10': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'WeightedEnsemble_L2': {'use_orig_features': False,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T3': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T4': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T5': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T6': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T7': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T8': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T9': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T10': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'WeightedEnsemble_L3': {'use_orig_features': False,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True}},
 'leaderboard':                   model   score_val  pred_time_val    fit_time  \
 0   WeightedEnsemble_L3  -35.774051       1.772058  181.241197   
 1   LightGBM_BAG_L2\T10  -35.981921       1.771059  158.507892   
 2    LightGBM_BAG_L2\T8  -36.060335       1.770059  158.524888   
 3    LightGBM_BAG_L2\T2  -36.171994       1.770059  158.733648   
 4    LightGBM_BAG_L2\T7  -36.286430       1.770059  158.686630   
 5    LightGBM_BAG_L2\T3  -36.406820       1.770059  158.835299   
 6    LightGBM_BAG_L2\T1  -36.440448       1.770059  158.692754   
 7   WeightedEnsemble_L2  -36.795580       0.418004   28.422191   
 8    LightGBM_BAG_L1\T8  -37.024016       0.236002   14.231187   
 9    LightGBM_BAG_L2\T5  -37.783677       1.770059  158.849647   
 10  LightGBM_BAG_L1\T10  -38.607579       0.181001   13.960008   
 11   LightGBM_BAG_L1\T3  -40.869191       0.234013   14.358388   
 12   LightGBM_BAG_L1\T1  -47.650433       0.205012   19.618656   
 13   LightGBM_BAG_L1\T7  -48.111992       0.153008   14.131077   
 14   LightGBM_BAG_L1\T2  -48.284649       0.161995   14.505001   
 15   LightGBM_BAG_L1\T5  -51.804726       0.172031   14.274050   
 16   LightGBM_BAG_L2\T9 -103.007016       1.770059  158.161762   
 17   LightGBM_BAG_L2\T6 -111.677585       1.770059  158.498611   
 18   LightGBM_BAG_L2\T4 -115.064413       1.770059  158.293782   
 19   LightGBM_BAG_L1\T6 -123.419154       0.162997   14.314400   
 20   LightGBM_BAG_L1\T9 -131.312991       0.126005   14.018013   
 21   LightGBM_BAG_L1\T4 -140.391777       0.137994   13.983833   
 
     pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  \
 0                 0.000999           0.263998            3       True   
 1                 0.001000          11.113278            2       True   
 2                 0.000000          11.130274            2       True   
 3                 0.000000          11.339034            2       True   
 4                 0.000000          11.292016            2       True   
 5                 0.000000          11.440685            2       True   
 6                 0.000000          11.298140            2       True   
 7                 0.001000           0.230996            2       True   
 8                 0.236002          14.231187            1       True   
 9                 0.000000          11.455033            2       True   
 10                0.181001          13.960008            1       True   
 11                0.234013          14.358388            1       True   
 12                0.205012          19.618656            1       True   
 13                0.153008          14.131077            1       True   
 14                0.161995          14.505001            1       True   
 15                0.172031          14.274050            1       True   
 16                0.000000          10.767148            2       True   
 17                0.000000          11.103997            2       True   
 18                0.000000          10.899168            2       True   
 19                0.162997          14.314400            1       True   
 20                0.126005          14.018013            1       True   
 21                0.137994          13.983833            1       True   
 
     fit_order  
 0          22  
 1          21  
 2          19  
 3          13  
 4          18  
 5          14  
 6          12  
 7          11  
 8           8  
 9          16  
 10         10  
 11          3  
 12          1  
 13          7  
 14          2  
 15          5  
 16         20  
 17         17  
 18         15  
 19          6  
 20          9  
 21          4  }

predictions_new_features_hpo2 = predictor_new_hpo2.predict(test,model=predictor_new_hpo2.get_model_best())
predictions_new_features_hpo2.head()

0    10.651279
1     6.327431
2     6.279728
3     6.315984
4     6.302880
Name: count, dtype: float32

# Remember to set all negative values to zero
predictions_new_features_hpo2.describe()

count    6493.000000
mean      190.663055
std       174.672501
min         5.210919
25%        43.650482
50%       148.237976
75%       283.945831
max       877.211304
Name: count, dtype: float64

predictions_new_features_hpo2[predictions_new_features_hpo2<0].count()

0

predictions_new_features_hpo2[predictions_new_features_hpo2<0]=0

submission_new_hpo2 = submission.copy(deep=True)

# Same submitting predictions
submission_new_hpo2["count"] = predictions_new_features_hpo2
submission_new_hpo2.to_csv("submission_new_hpo2.csv", index=False)

!kaggle competitions submit -c bike-sharing-demand -f submission_new_hpo2.csv -m "new features with hyperparameters2"

Successfully submitted to Bike Sharing Demand

  0%|          | 0.00/194k [00:00<?, ?B/s]
  4%|4         | 8.00k/194k [00:00<00:05, 32.1kB/s]
 95%|#########4| 184k/194k [00:00<00:00, 628kB/s]  
100%|##########| 194k/194k [00:04<00:00, 40.8kB/s]

!kaggle competitions submissions -c bike-sharing-demand 
#| tail -n +1 | head -n 6

fileName                     date                 description                         status    publicScore  privateScore  
---------------------------  -------------------  ----------------------------------  --------  -----------  ------------  
submission_new_hpo2.csv      2023-05-31 04:42:10  new features with hyperparameters2  complete  0.46765      0.46765       
submission_new_hpo1.csv      2023-05-31 03:08:31  new features with hyperparameters1  complete  0.46803      0.46803       
submission_new_hpo.csv       2023-05-31 01:32:59                                      complete  0.49844      0.49844       
submission_new_hpo.csv       2023-05-31 00:59:18  new features with hyperparameters   complete  0.49844      0.49844       
submission_new_features.csv  2023-05-30 06:32:08  new features                        complete  0.70588      0.70588       
submission.csv               2023-05-30 05:49:46  first raw submission                complete  1.80425      1.80425       

New Score of 0.46765

Step 7: Write a Report

Refer to the markdown file for the full report

Creating plots and table for report

baseline_leaderboard=predictor.leaderboard()
newfeatures_leaderboard=predictor_new_features.leaderboard()
hpo_leaderboard1=predictor_new_hpo.leaderboard()
hpo_leaderboard2=predictor_new_hpo1.leaderboard()
hpo_leaderboard3=predictor_new_hpo2.leaderboard()

                  model   score_val  pred_time_val    fit_time  pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  fit_order
0   WeightedEnsemble_L3  -35.774051       1.772058  181.241197                0.000999           0.263998            3       True         22
1   LightGBM_BAG_L2\T10  -35.981921       1.771059  158.507892                0.001000          11.113278            2       True         21
2    LightGBM_BAG_L2\T8  -36.060335       1.770059  158.524888                0.000000          11.130274            2       True         19
3    LightGBM_BAG_L2\T2  -36.171994       1.770059  158.733648                0.000000          11.339034            2       True         13
4    LightGBM_BAG_L2\T7  -36.286430       1.770059  158.686630                0.000000          11.292016            2       True         18
5    LightGBM_BAG_L2\T3  -36.406820       1.770059  158.835299                0.000000          11.440685            2       True         14
6    LightGBM_BAG_L2\T1  -36.440448       1.770059  158.692754                0.000000          11.298140            2       True         12
7   WeightedEnsemble_L2  -36.795580       0.418004   28.422191                0.001000           0.230996            2       True         11
8    LightGBM_BAG_L1\T8  -37.024016       0.236002   14.231187                0.236002          14.231187            1       True          8
9    LightGBM_BAG_L2\T5  -37.783677       1.770059  158.849647                0.000000          11.455033            2       True         16
10  LightGBM_BAG_L1\T10  -38.607579       0.181001   13.960008                0.181001          13.960008            1       True         10
11   LightGBM_BAG_L1\T3  -40.869191       0.234013   14.358388                0.234013          14.358388            1       True          3
12   LightGBM_BAG_L1\T1  -47.650433       0.205012   19.618656                0.205012          19.618656            1       True          1
13   LightGBM_BAG_L1\T7  -48.111992       0.153008   14.131077                0.153008          14.131077            1       True          7
14   LightGBM_BAG_L1\T2  -48.284649       0.161995   14.505001                0.161995          14.505001            1       True          2
15   LightGBM_BAG_L1\T5  -51.804726       0.172031   14.274050                0.172031          14.274050            1       True          5
16   LightGBM_BAG_L2\T9 -103.007016       1.770059  158.161762                0.000000          10.767148            2       True         20
17   LightGBM_BAG_L2\T6 -111.677585       1.770059  158.498611                0.000000          11.103997            2       True         17
18   LightGBM_BAG_L2\T4 -115.064413       1.770059  158.293782                0.000000          10.899168            2       True         15
19   LightGBM_BAG_L1\T6 -123.419154       0.162997   14.314400                0.162997          14.314400            1       True          6
20   LightGBM_BAG_L1\T9 -131.312991       0.126005   14.018013                0.126005          14.018013            1       True          9
21   LightGBM_BAG_L1\T4 -140.391777       0.137994   13.983833                0.137994          13.983833            1       True          4

baseline_model_score = abs(baseline_leaderboard['score_val'][0]) #50.545607#
newfeatures_model_score = abs(newfeatures_leaderboard['score_val'][0]) #29.890078#
hpo_model_score1 = abs(hpo_leaderboard1['score_val'][0]) #32.375607#
hpo_model_score2 = abs(hpo_leaderboard2['score_val'][0]) #36.428313#
hpo_model_score3 = abs(hpo_leaderboard3['score_val'][0]) #35.774051#

# Taking the top model score from each training run and creating a line plot to show improvement
# You can create these in the notebook and save them to PNG or use some other tool (e.g. google sheets, excel)
fig = pd.DataFrame(
    {
        "model": ["initial", "add_features", "hpo1","hpo2","hpo3"],
        "score": [baseline_model_score,newfeatures_model_score,hpo_model_score1,hpo_model_score2,hpo_model_score3]
    }
).plot(x="model", y="score",  ylabel= 'RMSE', style='-*', grid=True, figsize=(8, 6)).get_figure()
fig.savefig('img/model_train_score.png')

# Take the 3 kaggle scores and creating a line plot to show improvement
fig = pd.DataFrame(
    {
        "test_eval": ["initial", "add_features", "hpo1","hpo2","hpo3"],
        "score": [1.80425, 0.70588, 0.49844, 0.46803, 0.46765]
    }
).plot(x="test_eval", y="score", ylabel= 'RMSLE',style='-*',grid=True,figsize=(8, 6)).get_figure()

fig.savefig('img/model_test_score.png')

Hyperparameter table

# The 3 hyperparameters we tuned with the kaggle score as the result
pd.DataFrame({
    "model": ["initial", "add_features", "hpo","hpo1","hpo2"],
    "hpo1": ['default', 'default', 'auto',
             "GBM: num_boost_round=80, num_leaves(lower=10, upper=50, default=20)",
             "GBM: num_boost_round=80, num_leaves(lower=10, upper=50, default=20)"],
    "hpo2": ['default', 'default', 'auto',
             "NN_TORCH: num_epochs=10, learning_rate(1e-3, 1e-2, default=5e-3, log=True),activation('relu', 'softrelu', 'tanh'),layers([100],[200, 100])",
             "NN_TORCH: num_epochs(lower=8, upper=20, default=10), learning_rate(1e-3, 1e-2, default=5e-3, log=True),activation('relu', 'softrelu', 'tanh'),layers([100],[1000],[200, 100])"],
    "scheduler": ['default', 'default', 'ASHA','local','local'],
    "trial_time(seconds)": [600, 600,600,600,600],
    "score": [1.80425, 0.70588, 0.49844, 0.46803, 0.46765]
})

	model	hpo1	hpo2	scheduler	trial_time(seconds)	score
0	initial	default	default	default	600	1.80425
1	add_features	default	default	default	600	0.70588
2	hpo	auto	auto	ASHA	600	0.49844
3	hpo1	GBM: num_boost_round=80, num_leaves(lower=10, ...	NN_TORCH: num_epochs=10, learning_rate(1e-3, 1...	local	600	0.46803
4	hpo2	GBM: num_boost_round=80, num_leaves(lower=10, ...	NN_TORCH: num_epochs(lower=8, upper=20, defaul...	local	600	0.46765

Report: Predict Bike Sharing Demand with AutoGluon Solution

Noman Arshad

Initial Training

What did you realize when you tried to submit your predictions? What changes were needed to the output of the predictor to submit your results?

The output column (count - number of total rentals) should not be less than 0 as count can not be negative. So before submiting predictions we need to make sure that our predictions does not contain any negative value in predicted count.

What was the top ranked model that performed?

WeightedEnsemble_L2 with feature engineering and Hyper parameter optimization.

Exploratory data analysis and feature creation

What did the exploratory analysis find and how did you add additional features?

I checked correlation matrix of train df and found that initialy most correlated column was temp and realized that temp is not constant for every hour in a day and also for every week might have different avg temp. So I created some additional columns based on datetime provided to fetch hour of day, week of year, weekday etc. and it really helped in improving model performance.

How much better did your model preform after adding additional features and why do you think that is?

Model improved significantly after adding new features. I think it is due to the quality of feature. By adding creating highly correlated feature it helps model to learn better and find better decision boundary.

Hyper parameter tuning

How much better did your model preform after trying different hyper parameters?

Model performance improved with hyper parameter optimization but not that much as it improved by adding new features. From score table you can see by adding new features it improved significantly from 1.8 RMSLE to 0.7, and after HPO it improved by 0.2 RMSLE further.

If you were given more time with this dataset, where do you think you would spend more time?

I would like to spend more time on feature engineering to create new useful features that help model to learn decision boundary for better accuracy. With this I would also like to play with hyperparameters.

Create a table with the models you ran, the hyperparameters modified, and the kaggle score.

model	hpo1	hpo2	scheduler	trial_time (seconds)	score
initial	default	default	default	600	1.80425
add_features	default	default	default	600	0.70588
hpo	auto	auto	ASHA	600	0.49844
hpo1	GBM: num_boost_round=80, num_leaves(lower=10, upper=50, default=20)	NN_TORCH: num_epochs=10, learning_rate(1e-3, 1e-2, default=5e-3, log=True),activation('relu', 'softrelu', 'tanh'),layers([100],[200, 100])	local	600	0.46803
hpo2	GBM: num_boost_round=80, num_leaves(lower=10, upper=50, default=20)	NN_TORCH: num_epochs(lower=8, upper=20, default=10), learning_rate(1e-3, 1e-2, default=5e-3, log=True),activation('relu', 'softrelu', 'tanh'),layers([100],[1000],[200, 100])	local	600	0.46803

Create a line plot showing the top model score for the three (or more) training runs during the project.

Create a line plot showing the top kaggle score for the three (or more) prediction submissions during the project.

Summary

We can improve model performance by spending time on EDA and feature engineering. With better features we can train better models. After training model on data we can then fine tune model by playing with its hyper parameters.

References:

• https://auto.gluon.ai/dev/tutorials/multimodal/advanced_topics/hyperparameter_optimization.html
• https://docs.aws.amazon.com/sagemaker/latest/dg/autogluon-tabular-hyperparameters.html

=======

Predict Bike Sharing Demand with AutoGluon Template

Project: Predict Bike Sharing Demand with AutoGluon

This notebook is a template with each step that you need to complete for the project.

Please fill in your code where there are explicit ? markers in the notebook. You are welcome to add more cells and code as you see fit.

Once you have completed all the code implementations, please export your notebook as a HTML file so the reviews can view your code. Make sure you have all outputs correctly outputted.

File-> Export Notebook As... -> Export Notebook as HTML

There is a writeup to complete as well after all code implememtation is done. Please answer all questions and attach the necessary tables and charts. You can complete the writeup in either markdown or PDF.

Completing the code template and writeup template will cover all of the rubric points for this project.

The rubric contains "Stand Out Suggestions" for enhancing the project beyond the minimum requirements. The stand out suggestions are optional. If you decide to pursue the "stand out suggestions", you can include the code in this notebook and also discuss the results in the writeup file.

Step 1: Create an account with Kaggle

Create Kaggle Account and download API key

Below is example of steps to get the API username and key. Each student will have their own username and key.

1. Open account settings.
2. Scroll down to API and click Create New API Token.
3. Open up kaggle.json and use the username and key.

Step 2: Download the Kaggle dataset using the kaggle python library

Open up Sagemaker Studio and use starter template

1. Notebook should be using a ml.t3.medium instance (2 vCPU + 4 GiB)
2. Notebook should be using kernal: Python 3 (MXNet 1.8 Python 3.7 CPU Optimized)

Install packages

# !pip install -U pip
# !pip install -U setuptools wheel
# !pip install -U "mxnet<2.0.0" bokeh==2.0.1
# !pip install autogluon --no-cache-dir
# # Without --no-cache-dir, smaller aws instances may have trouble installing

Setup Kaggle API Key

# # create the .kaggle directory and an empty kaggle.json file
# !mkdir -p /root/.kaggle
# !touch /root/.kaggle/kaggle.json
# !chmod 600 /root/.kaggle/kaggle.json

# # Fill in your user name and key from creating the kaggle account and API token file
# import json
# kaggle_username = "FILL_IN_USERNAME"
# kaggle_key = "FILL_IN_KEY"

# # Save API token the kaggle.json file
# with open("/root/.kaggle/kaggle.json", "w") as f:
#     f.write(json.dumps({"username": kaggle_username, "key": kaggle_key}))

Download and explore dataset

Go to the bike sharing demand competition and agree to the terms

# # Download the dataset, it will be in a .zip file so you'll need to unzip it as well.
# !kaggle competitions download -c bike-sharing-demand
# # If you already downloaded it you can use the -o command to overwrite the file
# !unzip -o bike-sharing-demand.zip

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from autogluon.tabular import TabularPredictor
import autogluon.core as ag

import warnings
warnings.filterwarnings('ignore')

# Create the train dataset in pandas by reading the csv
# Set the parsing of the datetime column so you can use some of the `dt` features in pandas later
train = pd.read_csv('bike-sharing-demand/train.csv',parse_dates =['datetime'])

train.head()

	datetime	season	holiday	workingday	weather	temp	atemp	humidity	windspeed	casual	registered	count
0	2011-01-01 00:00:00	1	0	0	1	9.84	14.395	81	0.0	3	13	16
1	2011-01-01 01:00:00	1	0	0	1	9.02	13.635	80	0.0	8	32	40
2	2011-01-01 02:00:00	1	0	0	1	9.02	13.635	80	0.0	5	27	32
3	2011-01-01 03:00:00	1	0	0	1	9.84	14.395	75	0.0	3	10	13
4	2011-01-01 04:00:00	1	0	0	1	9.84	14.395	75	0.0	0	1	1

# Simple output of the train dataset to view some of the min/max/varition of the dataset features.

train.describe()

	season	holiday	workingday	weather	temp	atemp	humidity	windspeed	casual	registered	count
count	10886.000000	10886.000000	10886.000000	10886.000000	10886.00000	10886.000000	10886.000000	10886.000000	10886.000000	10886.000000	10886.000000
mean	2.506614	0.028569	0.680875	1.418427	20.23086	23.655084	61.886460	12.799395	36.021955	155.552177	191.574132
std	1.116174	0.166599	0.466159	0.633839	7.79159	8.474601	19.245033	8.164537	49.960477	151.039033	181.144454
min	1.000000	0.000000	0.000000	1.000000	0.82000	0.760000	0.000000	0.000000	0.000000	0.000000	1.000000
25%	2.000000	0.000000	0.000000	1.000000	13.94000	16.665000	47.000000	7.001500	4.000000	36.000000	42.000000
50%	3.000000	0.000000	1.000000	1.000000	20.50000	24.240000	62.000000	12.998000	17.000000	118.000000	145.000000
75%	4.000000	0.000000	1.000000	2.000000	26.24000	31.060000	77.000000	16.997900	49.000000	222.000000	284.000000
max	4.000000	1.000000	1.000000	4.000000	41.00000	45.455000	100.000000	56.996900	367.000000	886.000000	977.000000

# Create the test pandas dataframe in pandas by reading the csv, remember to parse the datetime!
test = pd.read_csv('bike-sharing-demand/test.csv',parse_dates =['datetime'])
test.head()

	datetime	season	holiday	workingday	weather	temp	atemp	humidity	windspeed
0	2011-01-20 00:00:00	1	0	1	1	10.66	11.365	56	26.0027
1	2011-01-20 01:00:00	1	0	1	1	10.66	13.635	56	0.0000
2	2011-01-20 02:00:00	1	0	1	1	10.66	13.635	56	0.0000
3	2011-01-20 03:00:00	1	0	1	1	10.66	12.880	56	11.0014
4	2011-01-20 04:00:00	1	0	1	1	10.66	12.880	56	11.0014

# Same thing as train and test dataset
submission = pd.read_csv('bike-sharing-demand/sampleSubmission.csv',parse_dates =['datetime'])
submission.head()

	datetime	count
0	2011-01-20 00:00:00	0
1	2011-01-20 01:00:00	0
2	2011-01-20 02:00:00	0
3	2011-01-20 03:00:00	0
4	2011-01-20 04:00:00	0

Step 3: Train a model using AutoGluon’s Tabular Prediction

Requirements:

• We are prediting count, so it is the label we are setting.
• Ignore casual and registered columns as they are also not present in the test dataset.
• Use the root_mean_squared_error as the metric to use for evaluation.
• Set a time limit of 10 minutes (600 seconds).
• Use the preset best_quality to focus on creating the best model.

train.head()

	datetime	season	holiday	workingday	weather	temp	atemp	humidity	windspeed	casual	registered	count
0	2011-01-01 00:00:00	1	0	0	1	9.84	14.395	81	0.0	3	13	16
1	2011-01-01 01:00:00	1	0	0	1	9.02	13.635	80	0.0	8	32	40
2	2011-01-01 02:00:00	1	0	0	1	9.02	13.635	80	0.0	5	27	32
3	2011-01-01 03:00:00	1	0	0	1	9.84	14.395	75	0.0	3	10	13
4	2011-01-01 04:00:00	1	0	0	1	9.84	14.395	75	0.0	0	1	1

predictor = TabularPredictor('count',problem_type='regression',learner_kwargs={"ignored_columns":['casual','registered']},
                             eval_metric='root_mean_squared_error').fit(train,time_limit=600,presets='best_quality')

No path specified. Models will be saved in: "AutogluonModels\ag-20230531_013647\"
Presets specified: ['best_quality']
Stack configuration (auto_stack=True): num_stack_levels=1, num_bag_folds=8, num_bag_sets=20
Beginning AutoGluon training ... Time limit = 600s
AutoGluon will save models to "AutogluonModels\ag-20230531_013647\"
AutoGluon Version:  0.7.0
Python Version:     3.8.16
Operating System:   Windows
Platform Machine:   AMD64
Platform Version:   10.0.19045
Train Data Rows:    10886
Train Data Columns: 11
Label Column: count
Preprocessing data ...
Using Feature Generators to preprocess the data ...
Dropping user-specified ignored columns: ['casual', 'registered']
Fitting AutoMLPipelineFeatureGenerator...
	Available Memory:                    7862.13 MB
	Train Data (Original)  Memory Usage: 0.78 MB (0.0% of available memory)
	Inferring data type of each feature based on column values. Set feature_metadata_in to manually specify special dtypes of the features.
	Stage 1 Generators:
		Fitting AsTypeFeatureGenerator...
			Note: Converting 2 features to boolean dtype as they only contain 2 unique values.
	Stage 2 Generators:
		Fitting FillNaFeatureGenerator...
	Stage 3 Generators:
		Fitting IdentityFeatureGenerator...
		Fitting DatetimeFeatureGenerator...
	Stage 4 Generators:
		Fitting DropUniqueFeatureGenerator...
	Types of features in original data (raw dtype, special dtypes):
		('datetime', []) : 1 | ['datetime']
		('float', [])    : 3 | ['temp', 'atemp', 'windspeed']
		('int', [])      : 5 | ['season', 'holiday', 'workingday', 'weather', 'humidity']
	Types of features in processed data (raw dtype, special dtypes):
		('float', [])                : 3 | ['temp', 'atemp', 'windspeed']
		('int', [])                  : 3 | ['season', 'weather', 'humidity']
		('int', ['bool'])            : 2 | ['holiday', 'workingday']
		('int', ['datetime_as_int']) : 5 | ['datetime', 'datetime.year', 'datetime.month', 'datetime.day', 'datetime.dayofweek']
	0.1s = Fit runtime
	9 features in original data used to generate 13 features in processed data.
	Train Data (Processed) Memory Usage: 0.98 MB (0.0% of available memory)
Data preprocessing and feature engineering runtime = 0.1s ...
AutoGluon will gauge predictive performance using evaluation metric: 'root_mean_squared_error'
	This metric's sign has been flipped to adhere to being higher_is_better. The metric score can be multiplied by -1 to get the metric value.
	To change this, specify the eval_metric parameter of Predictor()
AutoGluon will fit 2 stack levels (L1 to L2) ...
Fitting 11 L1 models ...
Fitting model: KNeighborsUnif_BAG_L1 ... Training model for up to 399.83s of the 599.9s of remaining time.
	-101.5882	 = Validation score   (-root_mean_squared_error)
	0.05s	 = Training   runtime
	0.02s	 = Validation runtime
Fitting model: KNeighborsDist_BAG_L1 ... Training model for up to 399.71s of the 599.78s of remaining time.
	-84.1464	 = Validation score   (-root_mean_squared_error)
	0.05s	 = Training   runtime
	0.03s	 = Validation runtime
Fitting model: LightGBMXT_BAG_L1 ... Training model for up to 399.6s of the 599.67s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-131.4609	 = Validation score   (-root_mean_squared_error)
	16.12s	 = Training   runtime
	6.0s	 = Validation runtime
Fitting model: LightGBM_BAG_L1 ... Training model for up to 372.34s of the 572.41s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-131.0542	 = Validation score   (-root_mean_squared_error)
	5.04s	 = Training   runtime
	0.9s	 = Validation runtime
Fitting model: RandomForestMSE_BAG_L1 ... Training model for up to 357.84s of the 557.91s of remaining time.
	-116.5521	 = Validation score   (-root_mean_squared_error)
	3.51s	 = Training   runtime
	0.4s	 = Validation runtime
Fitting model: CatBoost_BAG_L1 ... Training model for up to 353.64s of the 553.71s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-130.4612	 = Validation score   (-root_mean_squared_error)
	134.11s	 = Training   runtime
	0.06s	 = Validation runtime
Fitting model: ExtraTreesMSE_BAG_L1 ... Training model for up to 210.48s of the 410.55s of remaining time.
	-124.6023	 = Validation score   (-root_mean_squared_error)
	1.31s	 = Training   runtime
	0.38s	 = Validation runtime
Fitting model: NeuralNetFastAI_BAG_L1 ... Training model for up to 208.49s of the 408.56s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-135.8377	 = Validation score   (-root_mean_squared_error)
	20.38s	 = Training   runtime
	0.21s	 = Validation runtime
Fitting model: XGBoost_BAG_L1 ... Training model for up to 179.61s of the 379.67s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-131.6247	 = Validation score   (-root_mean_squared_error)
	4.23s	 = Training   runtime
	0.32s	 = Validation runtime
Fitting model: NeuralNetTorch_BAG_L1 ... Training model for up to 165.98s of the 366.05s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-137.6134	 = Validation score   (-root_mean_squared_error)
	99.5s	 = Training   runtime
	0.11s	 = Validation runtime
Fitting model: LightGBMLarge_BAG_L1 ... Training model for up to 57.96s of the 258.03s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-130.1323	 = Validation score   (-root_mean_squared_error)
	4.88s	 = Training   runtime
	0.53s	 = Validation runtime
Completed 1/20 k-fold bagging repeats ...
Fitting model: WeightedEnsemble_L2 ... Training model for up to 359.98s of the 244.09s of remaining time.
	-84.1464	 = Validation score   (-root_mean_squared_error)
	0.61s	 = Training   runtime
	0.02s	 = Validation runtime
Fitting 9 L2 models ...
Fitting model: LightGBMXT_BAG_L2 ... Training model for up to 243.44s of the 243.42s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-60.3213	 = Validation score   (-root_mean_squared_error)
	11.38s	 = Training   runtime
	2.87s	 = Validation runtime
Fitting model: LightGBM_BAG_L2 ... Training model for up to 222.42s of the 222.39s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-55.077	 = Validation score   (-root_mean_squared_error)
	3.59s	 = Training   runtime
	0.23s	 = Validation runtime
Fitting model: RandomForestMSE_BAG_L2 ... Training model for up to 209.32s of the 209.3s of remaining time.
	-53.3799	 = Validation score   (-root_mean_squared_error)
	11.79s	 = Training   runtime
	0.48s	 = Validation runtime
Fitting model: CatBoost_BAG_L2 ... Training model for up to 196.73s of the 196.72s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-55.5555	 = Validation score   (-root_mean_squared_error)
	28.35s	 = Training   runtime
	0.05s	 = Validation runtime
Fitting model: ExtraTreesMSE_BAG_L2 ... Training model for up to 159.62s of the 159.61s of remaining time.
	-54.3037	 = Validation score   (-root_mean_squared_error)
	2.7s	 = Training   runtime
	0.42s	 = Validation runtime
Fitting model: NeuralNetFastAI_BAG_L2 ... Training model for up to 156.22s of the 156.19s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-51.7163	 = Validation score   (-root_mean_squared_error)
	21.07s	 = Training   runtime
	0.24s	 = Validation runtime
Fitting model: XGBoost_BAG_L2 ... Training model for up to 126.3s of the 126.29s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-54.9604	 = Validation score   (-root_mean_squared_error)
	4.01s	 = Training   runtime
	0.11s	 = Validation runtime
Fitting model: NeuralNetTorch_BAG_L2 ... Training model for up to 112.81s of the 112.8s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-55.1251	 = Validation score   (-root_mean_squared_error)
	77.48s	 = Training   runtime
	0.19s	 = Validation runtime
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 26.22s of the 26.2s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-55.0695	 = Validation score   (-root_mean_squared_error)
	6.94s	 = Training   runtime
	0.23s	 = Validation runtime
Completed 1/20 k-fold bagging repeats ...
Fitting model: WeightedEnsemble_L3 ... Training model for up to 360.0s of the 9.98s of remaining time.
	-50.5274	 = Validation score   (-root_mean_squared_error)
	0.48s	 = Training   runtime
	0.0s	 = Validation runtime
AutoGluon training complete, total runtime = 590.54s ... Best model: "WeightedEnsemble_L3"
TabularPredictor saved. To load, use: predictor = TabularPredictor.load("AutogluonModels\ag-20230531_013647\")

Review AutoGluon's training run with ranking of models that did the best.

predictor.fit_summary()

*** Summary of fit() ***
Estimated performance of each model:
                     model   score_val  pred_time_val    fit_time  pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  fit_order
0      WeightedEnsemble_L3  -50.545607      11.096767  409.280485                0.000000           0.361998            3       True         22
1   NeuralNetFastAI_BAG_L2  -51.716262      10.008647  322.826800                0.270120          22.167076            2       True         18
2   RandomForestMSE_BAG_L2  -53.379886      10.171751  314.397344                0.433223          13.737620            2       True         15
3     ExtraTreesMSE_BAG_L2  -54.303663      10.179574  303.527697                0.441046           2.867972            2       True         17
4           XGBoost_BAG_L2  -54.960386       9.838179  304.831909                0.099651           4.172185            2       True         19
5     LightGBMLarge_BAG_L2  -55.069468      10.038877  305.921805                0.300349           5.262080            2       True         21
6          LightGBM_BAG_L2  -55.077004       9.937626  304.271100                0.199099           3.611376            2       True         14
7    NeuralNetTorch_BAG_L2  -55.314134       9.952379  370.145819                0.213851          69.486095            2       True         20
8          CatBoost_BAG_L2  -55.555501       9.775106  330.275181                0.036578          29.615457            2       True         16
9        LightGBMXT_BAG_L2  -60.321306      13.522628  313.045133                3.784101          12.385408            2       True         13
10     WeightedEnsemble_L2  -84.146423       0.021363    0.562025                0.000000           0.503019            2       True         12
11   KNeighborsDist_BAG_L1  -84.146423       0.021363    0.059006                0.021363           0.059006            1       True          2
12   KNeighborsUnif_BAG_L1 -101.588176       0.023003    0.055419                0.023003           0.055419            1       True          1
13  RandomForestMSE_BAG_L1 -116.552091       0.380218    3.619674                0.380218           3.619674            1       True          5
14    ExtraTreesMSE_BAG_L1 -124.602302       0.371037    1.416224                0.371037           1.416224            1       True          7
15    LightGBMLarge_BAG_L1 -130.132290       0.633200    5.427717                0.633200           5.427717            1       True         11
16         CatBoost_BAG_L1 -130.461205       0.052495  139.030226                0.052495         139.030226            1       True          6
17         LightGBM_BAG_L1 -131.054162       0.934174    5.051711                0.934174           5.051711            1       True          4
18       LightGBMXT_BAG_L1 -131.460909       6.613437   16.065701                6.613437          16.065701            1       True          3
19          XGBoost_BAG_L1 -131.624665       0.349599    4.290946                0.349599           4.290946            1       True          9
20  NeuralNetFastAI_BAG_L1 -135.837680       0.237846   21.203035                0.237846          21.203035            1       True          8
21   NeuralNetTorch_BAG_L1 -137.613441       0.122154  104.440064                0.122154         104.440064            1       True         10
Number of models trained: 22
Types of models trained:
{'StackerEnsembleModel_LGB', 'StackerEnsembleModel_CatBoost', 'StackerEnsembleModel_NNFastAiTabular', 'StackerEnsembleModel_XT', 'StackerEnsembleModel_RF', 'WeightedEnsembleModel', 'StackerEnsembleModel_TabularNeuralNetTorch', 'StackerEnsembleModel_KNN', 'StackerEnsembleModel_XGBoost'}
Bagging used: True  (with 8 folds)
Multi-layer stack-ensembling used: True  (with 3 levels)
Feature Metadata (Processed):
(raw dtype, special dtypes):
('float', [])                : 3 | ['temp', 'atemp', 'windspeed']
('int', [])                  : 3 | ['season', 'weather', 'humidity']
('int', ['bool'])            : 2 | ['holiday', 'workingday']
('int', ['datetime_as_int']) : 5 | ['datetime', 'datetime.year', 'datetime.month', 'datetime.day', 'datetime.dayofweek']
*** End of fit() summary ***

C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\plots.py:138: UserWarning: AutoGluon summary plots cannot be created because bokeh is not installed. To see plots, please do: "pip install bokeh==2.0.1"
  warnings.warn('AutoGluon summary plots cannot be created because bokeh is not installed. To see plots, please do: "pip install bokeh==2.0.1"')

{'model_types': {'KNeighborsUnif_BAG_L1': 'StackerEnsembleModel_KNN',
  'KNeighborsDist_BAG_L1': 'StackerEnsembleModel_KNN',
  'LightGBMXT_BAG_L1': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1': 'StackerEnsembleModel_LGB',
  'RandomForestMSE_BAG_L1': 'StackerEnsembleModel_RF',
  'CatBoost_BAG_L1': 'StackerEnsembleModel_CatBoost',
  'ExtraTreesMSE_BAG_L1': 'StackerEnsembleModel_XT',
  'NeuralNetFastAI_BAG_L1': 'StackerEnsembleModel_NNFastAiTabular',
  'XGBoost_BAG_L1': 'StackerEnsembleModel_XGBoost',
  'NeuralNetTorch_BAG_L1': 'StackerEnsembleModel_TabularNeuralNetTorch',
  'LightGBMLarge_BAG_L1': 'StackerEnsembleModel_LGB',
  'WeightedEnsemble_L2': 'WeightedEnsembleModel',
  'LightGBMXT_BAG_L2': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2': 'StackerEnsembleModel_LGB',
  'RandomForestMSE_BAG_L2': 'StackerEnsembleModel_RF',
  'CatBoost_BAG_L2': 'StackerEnsembleModel_CatBoost',
  'ExtraTreesMSE_BAG_L2': 'StackerEnsembleModel_XT',
  'NeuralNetFastAI_BAG_L2': 'StackerEnsembleModel_NNFastAiTabular',
  'XGBoost_BAG_L2': 'StackerEnsembleModel_XGBoost',
  'NeuralNetTorch_BAG_L2': 'StackerEnsembleModel_TabularNeuralNetTorch',
  'LightGBMLarge_BAG_L2': 'StackerEnsembleModel_LGB',
  'WeightedEnsemble_L3': 'WeightedEnsembleModel'},
 'model_performance': {'KNeighborsUnif_BAG_L1': -101.58817625927213,
  'KNeighborsDist_BAG_L1': -84.14642264302962,
  'LightGBMXT_BAG_L1': -131.46090891834504,
  'LightGBM_BAG_L1': -131.054161598899,
  'RandomForestMSE_BAG_L1': -116.55209143577434,
  'CatBoost_BAG_L1': -130.46120460893414,
  'ExtraTreesMSE_BAG_L1': -124.60230209225125,
  'NeuralNetFastAI_BAG_L1': -135.83768030668705,
  'XGBoost_BAG_L1': -131.62466543942023,
  'NeuralNetTorch_BAG_L1': -137.61344101796504,
  'LightGBMLarge_BAG_L1': -130.13228993716103,
  'WeightedEnsemble_L2': -84.14642264302962,
  'LightGBMXT_BAG_L2': -60.32130645032012,
  'LightGBM_BAG_L2': -55.07700383080456,
  'RandomForestMSE_BAG_L2': -53.37988550271052,
  'CatBoost_BAG_L2': -55.55550138438511,
  'ExtraTreesMSE_BAG_L2': -54.30366322835222,
  'NeuralNetFastAI_BAG_L2': -51.71626228633236,
  'XGBoost_BAG_L2': -54.96038583691514,
  'NeuralNetTorch_BAG_L2': -55.31413429144492,
  'LightGBMLarge_BAG_L2': -55.06946824246353,
  'WeightedEnsemble_L3': -50.54560736437441},
 'model_best': 'WeightedEnsemble_L3',
 'model_paths': {'KNeighborsUnif_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\KNeighborsUnif_BAG_L1\\',
  'KNeighborsDist_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\KNeighborsDist_BAG_L1\\',
  'LightGBMXT_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\LightGBMXT_BAG_L1\\',
  'LightGBM_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\LightGBM_BAG_L1\\',
  'RandomForestMSE_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\RandomForestMSE_BAG_L1\\',
  'CatBoost_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\CatBoost_BAG_L1\\',
  'ExtraTreesMSE_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\ExtraTreesMSE_BAG_L1\\',
  'NeuralNetFastAI_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\NeuralNetFastAI_BAG_L1\\',
  'XGBoost_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\XGBoost_BAG_L1\\',
  'NeuralNetTorch_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\NeuralNetTorch_BAG_L1\\',
  'LightGBMLarge_BAG_L1': 'AutogluonModels\\ag-20230530_052724\\models\\LightGBMLarge_BAG_L1\\',
  'WeightedEnsemble_L2': 'AutogluonModels\\ag-20230530_052724\\models\\WeightedEnsemble_L2\\',
  'LightGBMXT_BAG_L2': 'AutogluonModels\\ag-20230530_052724\\models\\LightGBMXT_BAG_L2\\',
  'LightGBM_BAG_L2': 'AutogluonModels\\ag-20230530_052724\\models\\LightGBM_BAG_L2\\',
  'RandomForestMSE_BAG_L2': 'AutogluonModels\\ag-20230530_052724\\models\\RandomForestMSE_BAG_L2\\',
  'CatBoost_BAG_L2': 'AutogluonModels\\ag-20230530_052724\\models\\CatBoost_BAG_L2\\',
  'ExtraTreesMSE_BAG_L2': 'AutogluonModels\\ag-20230530_052724\\models\\ExtraTreesMSE_BAG_L2\\',
  'NeuralNetFastAI_BAG_L2': 'AutogluonModels\\ag-20230530_052724\\models\\NeuralNetFastAI_BAG_L2\\',
  'XGBoost_BAG_L2': 'AutogluonModels\\ag-20230530_052724\\models\\XGBoost_BAG_L2\\',
  'NeuralNetTorch_BAG_L2': 'AutogluonModels\\ag-20230530_052724\\models\\NeuralNetTorch_BAG_L2\\',
  'LightGBMLarge_BAG_L2': 'AutogluonModels\\ag-20230530_052724\\models\\LightGBMLarge_BAG_L2\\',
  'WeightedEnsemble_L3': 'AutogluonModels\\ag-20230530_052724\\models\\WeightedEnsemble_L3\\'},
 'model_fit_times': {'KNeighborsUnif_BAG_L1': 0.0554194450378418,
  'KNeighborsDist_BAG_L1': 0.0590062141418457,
  'LightGBMXT_BAG_L1': 16.065701246261597,
  'LightGBM_BAG_L1': 5.051711320877075,
  'RandomForestMSE_BAG_L1': 3.619673728942871,
  'CatBoost_BAG_L1': 139.03022646903992,
  'ExtraTreesMSE_BAG_L1': 1.4162240028381348,
  'NeuralNetFastAI_BAG_L1': 21.2030348777771,
  'XGBoost_BAG_L1': 4.290945768356323,
  'NeuralNetTorch_BAG_L1': 104.44006395339966,
  'LightGBMLarge_BAG_L1': 5.427717447280884,
  'WeightedEnsemble_L2': 0.5030190944671631,
  'LightGBMXT_BAG_L2': 12.385408163070679,
  'LightGBM_BAG_L2': 3.6113758087158203,
  'RandomForestMSE_BAG_L2': 13.737619876861572,
  'CatBoost_BAG_L2': 29.6154568195343,
  'ExtraTreesMSE_BAG_L2': 2.8679721355438232,
  'NeuralNetFastAI_BAG_L2': 22.167075872421265,
  'XGBoost_BAG_L2': 4.172184705734253,
  'NeuralNetTorch_BAG_L2': 69.48609471321106,
  'LightGBMLarge_BAG_L2': 5.262080192565918,
  'WeightedEnsemble_L3': 0.3619976043701172},
 'model_pred_times': {'KNeighborsUnif_BAG_L1': 0.023003101348876953,
  'KNeighborsDist_BAG_L1': 0.021363496780395508,
  'LightGBMXT_BAG_L1': 6.613437175750732,
  'LightGBM_BAG_L1': 0.9341740608215332,
  'RandomForestMSE_BAG_L1': 0.3802177906036377,
  'CatBoost_BAG_L1': 0.05249500274658203,
  'ExtraTreesMSE_BAG_L1': 0.37103724479675293,
  'NeuralNetFastAI_BAG_L1': 0.23784637451171875,
  'XGBoost_BAG_L1': 0.34959936141967773,
  'NeuralNetTorch_BAG_L1': 0.12215352058410645,
  'LightGBMLarge_BAG_L1': 0.6332004070281982,
  'WeightedEnsemble_L2': 0.0,
  'LightGBMXT_BAG_L2': 3.7841007709503174,
  'LightGBM_BAG_L2': 0.19909882545471191,
  'RandomForestMSE_BAG_L2': 0.43322300910949707,
  'CatBoost_BAG_L2': 0.03657817840576172,
  'ExtraTreesMSE_BAG_L2': 0.44104623794555664,
  'NeuralNetFastAI_BAG_L2': 0.27011966705322266,
  'XGBoost_BAG_L2': 0.09965109825134277,
  'NeuralNetTorch_BAG_L2': 0.2138509750366211,
  'LightGBMLarge_BAG_L2': 0.30034899711608887,
  'WeightedEnsemble_L3': 0.0},
 'num_bag_folds': 8,
 'max_stack_level': 3,
 'model_hyperparams': {'KNeighborsUnif_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'KNeighborsDist_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'LightGBMXT_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'RandomForestMSE_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'CatBoost_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'ExtraTreesMSE_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'NeuralNetFastAI_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'XGBoost_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'NeuralNetTorch_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBMLarge_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'WeightedEnsemble_L2': {'use_orig_features': False,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBMXT_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'RandomForestMSE_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'CatBoost_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'ExtraTreesMSE_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'NeuralNetFastAI_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'XGBoost_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'NeuralNetTorch_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBMLarge_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'WeightedEnsemble_L3': {'use_orig_features': False,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True}},
 'leaderboard':                      model   score_val  pred_time_val    fit_time  \
 0      WeightedEnsemble_L3  -50.545607      11.096767  409.280485   
 1   NeuralNetFastAI_BAG_L2  -51.716262      10.008647  322.826800   
 2   RandomForestMSE_BAG_L2  -53.379886      10.171751  314.397344   
 3     ExtraTreesMSE_BAG_L2  -54.303663      10.179574  303.527697   
 4           XGBoost_BAG_L2  -54.960386       9.838179  304.831909   
 5     LightGBMLarge_BAG_L2  -55.069468      10.038877  305.921805   
 6          LightGBM_BAG_L2  -55.077004       9.937626  304.271100   
 7    NeuralNetTorch_BAG_L2  -55.314134       9.952379  370.145819   
 8          CatBoost_BAG_L2  -55.555501       9.775106  330.275181   
 9        LightGBMXT_BAG_L2  -60.321306      13.522628  313.045133   
 10     WeightedEnsemble_L2  -84.146423       0.021363    0.562025   
 11   KNeighborsDist_BAG_L1  -84.146423       0.021363    0.059006   
 12   KNeighborsUnif_BAG_L1 -101.588176       0.023003    0.055419   
 13  RandomForestMSE_BAG_L1 -116.552091       0.380218    3.619674   
 14    ExtraTreesMSE_BAG_L1 -124.602302       0.371037    1.416224   
 15    LightGBMLarge_BAG_L1 -130.132290       0.633200    5.427717   
 16         CatBoost_BAG_L1 -130.461205       0.052495  139.030226   
 17         LightGBM_BAG_L1 -131.054162       0.934174    5.051711   
 18       LightGBMXT_BAG_L1 -131.460909       6.613437   16.065701   
 19          XGBoost_BAG_L1 -131.624665       0.349599    4.290946   
 20  NeuralNetFastAI_BAG_L1 -135.837680       0.237846   21.203035   
 21   NeuralNetTorch_BAG_L1 -137.613441       0.122154  104.440064   
 
     pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  \
 0                 0.000000           0.361998            3       True   
 1                 0.270120          22.167076            2       True   
 2                 0.433223          13.737620            2       True   
 3                 0.441046           2.867972            2       True   
 4                 0.099651           4.172185            2       True   
 5                 0.300349           5.262080            2       True   
 6                 0.199099           3.611376            2       True   
 7                 0.213851          69.486095            2       True   
 8                 0.036578          29.615457            2       True   
 9                 3.784101          12.385408            2       True   
 10                0.000000           0.503019            2       True   
 11                0.021363           0.059006            1       True   
 12                0.023003           0.055419            1       True   
 13                0.380218           3.619674            1       True   
 14                0.371037           1.416224            1       True   
 15                0.633200           5.427717            1       True   
 16                0.052495         139.030226            1       True   
 17                0.934174           5.051711            1       True   
 18                6.613437          16.065701            1       True   
 19                0.349599           4.290946            1       True   
 20                0.237846          21.203035            1       True   
 21                0.122154         104.440064            1       True   
 
     fit_order  
 0          22  
 1          18  
 2          15  
 3          17  
 4          19  
 5          21  
 6          14  
 7          20  
 8          16  
 9          13  
 10         12  
 11          2  
 12          1  
 13          5  
 14          7  
 15         11  
 16          6  
 17          4  
 18          3  
 19          9  
 20          8  
 21         10  }

Create predictions from test dataset

best_model_name = predictor.get_model_best()

predictions = predictor.predict(test,model=best_model_name)
predictions.head()

0    24.909117
1    39.908840
2    44.751022
3    48.349266
4    50.776348
Name: count, dtype: float32

NOTE: Kaggle will reject the submission if we don't set everything to be > 0.

# Describe the `predictions` series to see if there are any negative values
predictions.describe()

count    6493.000000
mean       99.896164
std        88.322205
min         0.362242
25%        21.798826
50%        67.599335
75%       168.456116
max       351.272461
Name: count, dtype: float64

# How many negative values do we have?
predictions[predictions<0].count()

0

# Set them to zero
predictions[predictions<0]=0

Set predictions to submission dataframe, save, and submit

submission["count"] = predictions
submission.to_csv("submission.csv", index=False)

!kaggle competitions submit -c bike-sharing-demand -f submission.csv -m "first raw submission"

Successfully submitted to Bike Sharing Demand

  0%|          | 0.00/195k [00:00<?, ?B/s]
  4%|4         | 8.00k/195k [01:24<32:49, 97.1B/s]
 94%|#########4| 184k/195k [01:24<00:03, 3.14kB/s]
100%|##########| 195k/195k [01:28<00:00, 2.25kB/s]

View submission via the command line or in the web browser under the competition's page - My Submissions

!kaggle competitions submissions -c bike-sharing-demand
#| tail -n +1 | head -n 6

fileName        date                 description           status    publicScore  privateScore  
--------------  -------------------  --------------------  --------  -----------  ------------  
submission.csv  2023-05-30 05:49:46  first raw submission  complete  1.80425      1.80425       

Initial score of 1.80425

Step 4: Exploratory Data Analysis and Creating an additional feature

• Any additional feature will do, but a great suggestion would be to separate out the datetime into hour, day, or month parts.

corr=train.corr()
sns.heatmap(corr,  cmap="Blues", annot=False,
        xticklabels=corr.columns,
        yticklabels=corr.columns);

# Create a histogram of all features to show the distribution of each one relative to the data. This is part of the exploritory data analysis
fig,ax=plt.subplots(figsize=[20,15]);
train.hist(edgecolor='black', grid=False,ax=ax);

train.datetime.dt.day_name()

0         Saturday
1         Saturday
2         Saturday
3         Saturday
4         Saturday
           ...    
10881    Wednesday
10882    Wednesday
10883    Wednesday
10884    Wednesday
10885    Wednesday
Name: datetime, Length: 10886, dtype: object

# create a new feature
train['year'] = train.datetime.dt.year
train['week'] = train.datetime.dt.week
train['hour'] = train.datetime.dt.hour
train['weekday'] = train.datetime.dt.day_name()
test['year'] = test.datetime.dt.year
test['week'] = test.datetime.dt.week
test['hour'] = test.datetime.dt.hour
test['weekday'] = test.datetime.dt.day_name()

Make category types for these so models know they are not just numbers

• AutoGluon originally sees these as ints, but in reality they are int representations of a category.
• Setting the dtype to category will classify these as categories in AutoGluon.

train["season"] = train["season"].astype('category')
train["weather"] = train["weather"].astype('category')
test["season"] = test["season"].astype('category')
test["weather"] = test["weather"].astype('category')

train['year'] = train["year"].astype('category')
# train['week'] = train["week"].astype('category')
# train['hour'] = train["hour"].astype('category')
train['weekday'] = train["weekday"].astype('category')
test['year'] = test["year"].astype('category')
# test['week'] = test["week"].astype('category')
# test['hour'] = test["hour"].astype('category')
test['weekday'] = test["weekday"].astype('category')

# View are new feature
train.head()

	datetime	season	holiday	workingday	weather	temp	atemp	humidity	windspeed	casual	registered	count	year	week	hour	weekday
0	2011-01-01 00:00:00	1	0	0	1	9.84	14.395	81	0.0	3	13	16	2011	52	0	Saturday
1	2011-01-01 01:00:00	1	0	0	1	9.02	13.635	80	0.0	8	32	40	2011	52	1	Saturday
2	2011-01-01 02:00:00	1	0	0	1	9.02	13.635	80	0.0	5	27	32	2011	52	2	Saturday
3	2011-01-01 03:00:00	1	0	0	1	9.84	14.395	75	0.0	3	10	13	2011	52	3	Saturday
4	2011-01-01 04:00:00	1	0	0	1	9.84	14.395	75	0.0	0	1	1	2011	52	4	Saturday

corr=train.corr()
sns.heatmap(corr,  cmap="Blues", annot=False,
        xticklabels=corr.columns,
        yticklabels=corr.columns);

# View histogram of all features again now with the hour feature
fig,ax=plt.subplots(figsize=[20,15]);
train.hist(edgecolor='black', grid=False,ax=ax);

Step 5: Rerun the model with the same settings as before, just with more features

predictor_new_features = TabularPredictor('count',problem_type='regression',learner_kwargs={"ignored_columns":['casual','registered']},
                             eval_metric='root_mean_squared_error').fit(train,time_limit=600,presets='best_quality')

No path specified. Models will be saved in: "AutogluonModels\ag-20230530_061306\"
Presets specified: ['best_quality']
Stack configuration (auto_stack=True): num_stack_levels=1, num_bag_folds=8, num_bag_sets=20
Beginning AutoGluon training ... Time limit = 600s
AutoGluon will save models to "AutogluonModels\ag-20230530_061306\"
AutoGluon Version:  0.7.0
Python Version:     3.8.16
Operating System:   Windows
Platform Machine:   AMD64
Platform Version:   10.0.19045
Train Data Rows:    10886
Train Data Columns: 15
Label Column: count
Preprocessing data ...
Using Feature Generators to preprocess the data ...
Dropping user-specified ignored columns: ['casual', 'registered']
Fitting AutoMLPipelineFeatureGenerator...
	Available Memory:                    6493.93 MB
	Train Data (Original)  Memory Usage: 1.59 MB (0.0% of available memory)
	Inferring data type of each feature based on column values. Set feature_metadata_in to manually specify special dtypes of the features.
	Stage 1 Generators:
		Fitting AsTypeFeatureGenerator...
			Note: Converting 3 features to boolean dtype as they only contain 2 unique values.
	Stage 2 Generators:
		Fitting FillNaFeatureGenerator...
	Stage 3 Generators:
		Fitting IdentityFeatureGenerator...
		Fitting CategoryFeatureGenerator...
			Fitting CategoryMemoryMinimizeFeatureGenerator...
		Fitting DatetimeFeatureGenerator...
	Stage 4 Generators:
		Fitting DropUniqueFeatureGenerator...
	Types of features in original data (raw dtype, special dtypes):
		('category', []) : 2 | ['season', 'weather']
		('datetime', []) : 1 | ['datetime']
		('float', [])    : 3 | ['temp', 'atemp', 'windspeed']
		('int', [])      : 6 | ['holiday', 'workingday', 'humidity', 'year', 'week', ...]
		('object', [])   : 1 | ['weekday']
	Types of features in processed data (raw dtype, special dtypes):
		('category', [])             : 3 | ['season', 'weather', 'weekday']
		('float', [])                : 3 | ['temp', 'atemp', 'windspeed']
		('int', [])                  : 3 | ['humidity', 'week', 'hour']
		('int', ['bool'])            : 3 | ['holiday', 'workingday', 'year']
		('int', ['datetime_as_int']) : 5 | ['datetime', 'datetime.year', 'datetime.month', 'datetime.day', 'datetime.dayofweek']
	0.1s = Fit runtime
	13 features in original data used to generate 17 features in processed data.
	Train Data (Processed) Memory Usage: 1.02 MB (0.0% of available memory)
Data preprocessing and feature engineering runtime = 0.13s ...
AutoGluon will gauge predictive performance using evaluation metric: 'root_mean_squared_error'
	This metric's sign has been flipped to adhere to being higher_is_better. The metric score can be multiplied by -1 to get the metric value.
	To change this, specify the eval_metric parameter of Predictor()
AutoGluon will fit 2 stack levels (L1 to L2) ...
Fitting 11 L1 models ...
Fitting model: KNeighborsUnif_BAG_L1 ... Training model for up to 399.81s of the 599.86s of remaining time.
	-101.5882	 = Validation score   (-root_mean_squared_error)
	0.05s	 = Training   runtime
	0.02s	 = Validation runtime
Fitting model: KNeighborsDist_BAG_L1 ... Training model for up to 399.69s of the 599.74s of remaining time.
	-84.1464	 = Validation score   (-root_mean_squared_error)
	0.06s	 = Training   runtime
	0.03s	 = Validation runtime
Fitting model: LightGBMXT_BAG_L1 ... Training model for up to 399.58s of the 599.63s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-34.0003	 = Validation score   (-root_mean_squared_error)
	23.42s	 = Training   runtime
	11.91s	 = Validation runtime
Fitting model: LightGBM_BAG_L1 ... Training model for up to 363.28s of the 563.33s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.8875	 = Validation score   (-root_mean_squared_error)
	15.95s	 = Training   runtime
	2.69s	 = Validation runtime
Fitting model: RandomForestMSE_BAG_L1 ... Training model for up to 336.91s of the 536.96s of remaining time.
	-38.2637	 = Validation score   (-root_mean_squared_error)
	3.91s	 = Training   runtime
	0.39s	 = Validation runtime
Fitting model: CatBoost_BAG_L1 ... Training model for up to 332.28s of the 532.33s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.9105	 = Validation score   (-root_mean_squared_error)
	266.12s	 = Training   runtime
	0.14s	 = Validation runtime
Fitting model: ExtraTreesMSE_BAG_L1 ... Training model for up to 57.83s of the 257.89s of remaining time.
	-37.9605	 = Validation score   (-root_mean_squared_error)
	2.37s	 = Training   runtime
	0.44s	 = Validation runtime
Fitting model: NeuralNetFastAI_BAG_L1 ... Training model for up to 54.68s of the 254.74s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-44.205	 = Validation score   (-root_mean_squared_error)
	23.72s	 = Training   runtime
	0.39s	 = Validation runtime
Fitting model: XGBoost_BAG_L1 ... Training model for up to 22.03s of the 222.09s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-34.6233	 = Validation score   (-root_mean_squared_error)
	12.38s	 = Training   runtime
	0.71s	 = Validation runtime
Completed 1/20 k-fold bagging repeats ...
Fitting model: WeightedEnsemble_L2 ... Training model for up to 360.0s of the 199.53s of remaining time.
	-31.9455	 = Validation score   (-root_mean_squared_error)
	0.4s	 = Training   runtime
	0.0s	 = Validation runtime
Fitting 9 L2 models ...
Fitting model: LightGBMXT_BAG_L2 ... Training model for up to 199.11s of the 199.1s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-31.1964	 = Validation score   (-root_mean_squared_error)
	4.94s	 = Training   runtime
	0.54s	 = Validation runtime
Fitting model: LightGBM_BAG_L2 ... Training model for up to 185.05s of the 185.04s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-30.7771	 = Validation score   (-root_mean_squared_error)
	4.03s	 = Training   runtime
	0.24s	 = Validation runtime
Fitting model: RandomForestMSE_BAG_L2 ... Training model for up to 171.53s of the 171.52s of remaining time.
	-31.8463	 = Validation score   (-root_mean_squared_error)
	12.21s	 = Training   runtime
	0.46s	 = Validation runtime
Fitting model: CatBoost_BAG_L2 ... Training model for up to 158.53s of the 158.52s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-30.4971	 = Validation score   (-root_mean_squared_error)
	126.81s	 = Training   runtime
	0.05s	 = Validation runtime
Fitting model: ExtraTreesMSE_BAG_L2 ... Training model for up to 22.93s of the 22.93s of remaining time.
	-31.6902	 = Validation score   (-root_mean_squared_error)
	2.98s	 = Training   runtime
	0.44s	 = Validation runtime
Fitting model: NeuralNetFastAI_BAG_L2 ... Training model for up to 19.22s of the 19.22s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-30.3001	 = Validation score   (-root_mean_squared_error)
	18.73s	 = Training   runtime
	0.31s	 = Validation runtime
Completed 1/20 k-fold bagging repeats ...
Fitting model: WeightedEnsemble_L3 ... Training model for up to 360.0s of the -8.14s of remaining time.
	-29.8901	 = Validation score   (-root_mean_squared_error)
	0.28s	 = Training   runtime
	0.0s	 = Validation runtime
AutoGluon training complete, total runtime = 608.44s ... Best model: "WeightedEnsemble_L3"
TabularPredictor saved. To load, use: predictor = TabularPredictor.load("AutogluonModels\ag-20230530_061306\")

predictor_new_features.fit_summary()

*** Summary of fit() ***
Estimated performance of each model:
                     model   score_val  pred_time_val    fit_time  pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  fit_order
0      WeightedEnsemble_L3  -29.890078      17.328178  497.813932                0.000000           0.277118            3       True         17
1   NeuralNetFastAI_BAG_L2  -30.300083      17.032513  366.699103                0.309780          18.725494            2       True         16
2          CatBoost_BAG_L2  -30.497057      16.777017  474.781693                0.054284         126.808084            2       True         14
3          LightGBM_BAG_L2  -30.777089      16.964114  352.003236                0.241381           4.029627            2       True         12
4        LightGBMXT_BAG_L2  -31.196428      17.262372  352.911093                0.539639           4.937484            2       True         11
5     ExtraTreesMSE_BAG_L2  -31.690163      17.162664  350.954443                0.439931           2.980835            2       True         15
6   RandomForestMSE_BAG_L2  -31.846290      17.186521  360.183255                0.463788          12.209647            2       True         13
7      WeightedEnsemble_L2  -31.945469      15.874762  322.231183                0.000000           0.399840            2       True         10
8          LightGBM_BAG_L1  -33.887545       2.687760   15.945202                2.687760          15.945202            1       True          4
9          CatBoost_BAG_L1  -33.910528       0.140069  266.118776                0.140069         266.118776            1       True          6
10       LightGBMXT_BAG_L1  -34.000297      11.907729   23.421796               11.907729          23.421796            1       True          3
11          XGBoost_BAG_L1  -34.623349       0.713807   12.375826                0.713807          12.375826            1       True          9
12    ExtraTreesMSE_BAG_L1  -37.960508       0.441126    2.371667                0.441126           2.371667            1       True          7
13  RandomForestMSE_BAG_L1  -38.263675       0.394188    3.912401                0.394188           3.912401            1       True          5
14  NeuralNetFastAI_BAG_L1  -44.205036       0.391262   23.719739                0.391262          23.719739            1       True          8
15   KNeighborsDist_BAG_L1  -84.146423       0.031208    0.057342                0.031208           0.057342            1       True          2
16   KNeighborsUnif_BAG_L1 -101.588176       0.015584    0.050859                0.015584           0.050859            1       True          1
Number of models trained: 17
Types of models trained:
{'StackerEnsembleModel_LGB', 'StackerEnsembleModel_CatBoost', 'StackerEnsembleModel_NNFastAiTabular', 'StackerEnsembleModel_XT', 'StackerEnsembleModel_RF', 'WeightedEnsembleModel', 'StackerEnsembleModel_KNN', 'StackerEnsembleModel_XGBoost'}
Bagging used: True  (with 8 folds)
Multi-layer stack-ensembling used: True  (with 3 levels)
Feature Metadata (Processed):
(raw dtype, special dtypes):
('category', [])             : 3 | ['season', 'weather', 'weekday']
('float', [])                : 3 | ['temp', 'atemp', 'windspeed']
('int', [])                  : 3 | ['humidity', 'week', 'hour']
('int', ['bool'])            : 3 | ['holiday', 'workingday', 'year']
('int', ['datetime_as_int']) : 5 | ['datetime', 'datetime.year', 'datetime.month', 'datetime.day', 'datetime.dayofweek']
*** End of fit() summary ***

{'model_types': {'KNeighborsUnif_BAG_L1': 'StackerEnsembleModel_KNN',
  'KNeighborsDist_BAG_L1': 'StackerEnsembleModel_KNN',
  'LightGBMXT_BAG_L1': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1': 'StackerEnsembleModel_LGB',
  'RandomForestMSE_BAG_L1': 'StackerEnsembleModel_RF',
  'CatBoost_BAG_L1': 'StackerEnsembleModel_CatBoost',
  'ExtraTreesMSE_BAG_L1': 'StackerEnsembleModel_XT',
  'NeuralNetFastAI_BAG_L1': 'StackerEnsembleModel_NNFastAiTabular',
  'XGBoost_BAG_L1': 'StackerEnsembleModel_XGBoost',
  'WeightedEnsemble_L2': 'WeightedEnsembleModel',
  'LightGBMXT_BAG_L2': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2': 'StackerEnsembleModel_LGB',
  'RandomForestMSE_BAG_L2': 'StackerEnsembleModel_RF',
  'CatBoost_BAG_L2': 'StackerEnsembleModel_CatBoost',
  'ExtraTreesMSE_BAG_L2': 'StackerEnsembleModel_XT',
  'NeuralNetFastAI_BAG_L2': 'StackerEnsembleModel_NNFastAiTabular',
  'WeightedEnsemble_L3': 'WeightedEnsembleModel'},
 'model_performance': {'KNeighborsUnif_BAG_L1': -101.58817625927213,
  'KNeighborsDist_BAG_L1': -84.14642264302962,
  'LightGBMXT_BAG_L1': -34.00029724644784,
  'LightGBM_BAG_L1': -33.88754549654657,
  'RandomForestMSE_BAG_L1': -38.263675022933384,
  'CatBoost_BAG_L1': -33.910528160775904,
  'ExtraTreesMSE_BAG_L1': -37.96050753822019,
  'NeuralNetFastAI_BAG_L1': -44.205036457713064,
  'XGBoost_BAG_L1': -34.623348652304394,
  'WeightedEnsemble_L2': -31.945468585211955,
  'LightGBMXT_BAG_L2': -31.1964283492438,
  'LightGBM_BAG_L2': -30.777088546205622,
  'RandomForestMSE_BAG_L2': -31.84629005491563,
  'CatBoost_BAG_L2': -30.497056547941266,
  'ExtraTreesMSE_BAG_L2': -31.6901633765071,
  'NeuralNetFastAI_BAG_L2': -30.300082951575046,
  'WeightedEnsemble_L3': -29.890077901192186},
 'model_best': 'WeightedEnsemble_L3',
 'model_paths': {'KNeighborsUnif_BAG_L1': 'AutogluonModels\\ag-20230530_061306\\models\\KNeighborsUnif_BAG_L1\\',
  'KNeighborsDist_BAG_L1': 'AutogluonModels\\ag-20230530_061306\\models\\KNeighborsDist_BAG_L1\\',
  'LightGBMXT_BAG_L1': 'AutogluonModels\\ag-20230530_061306\\models\\LightGBMXT_BAG_L1\\',
  'LightGBM_BAG_L1': 'AutogluonModels\\ag-20230530_061306\\models\\LightGBM_BAG_L1\\',
  'RandomForestMSE_BAG_L1': 'AutogluonModels\\ag-20230530_061306\\models\\RandomForestMSE_BAG_L1\\',
  'CatBoost_BAG_L1': 'AutogluonModels\\ag-20230530_061306\\models\\CatBoost_BAG_L1\\',
  'ExtraTreesMSE_BAG_L1': 'AutogluonModels\\ag-20230530_061306\\models\\ExtraTreesMSE_BAG_L1\\',
  'NeuralNetFastAI_BAG_L1': 'AutogluonModels\\ag-20230530_061306\\models\\NeuralNetFastAI_BAG_L1\\',
  'XGBoost_BAG_L1': 'AutogluonModels\\ag-20230530_061306\\models\\XGBoost_BAG_L1\\',
  'WeightedEnsemble_L2': 'AutogluonModels\\ag-20230530_061306\\models\\WeightedEnsemble_L2\\',
  'LightGBMXT_BAG_L2': 'AutogluonModels\\ag-20230530_061306\\models\\LightGBMXT_BAG_L2\\',
  'LightGBM_BAG_L2': 'AutogluonModels\\ag-20230530_061306\\models\\LightGBM_BAG_L2\\',
  'RandomForestMSE_BAG_L2': 'AutogluonModels\\ag-20230530_061306\\models\\RandomForestMSE_BAG_L2\\',
  'CatBoost_BAG_L2': 'AutogluonModels\\ag-20230530_061306\\models\\CatBoost_BAG_L2\\',
  'ExtraTreesMSE_BAG_L2': 'AutogluonModels\\ag-20230530_061306\\models\\ExtraTreesMSE_BAG_L2\\',
  'NeuralNetFastAI_BAG_L2': 'AutogluonModels\\ag-20230530_061306\\models\\NeuralNetFastAI_BAG_L2\\',
  'WeightedEnsemble_L3': 'AutogluonModels\\ag-20230530_061306\\models\\WeightedEnsemble_L3\\'},
 'model_fit_times': {'KNeighborsUnif_BAG_L1': 0.05085945129394531,
  'KNeighborsDist_BAG_L1': 0.0573420524597168,
  'LightGBMXT_BAG_L1': 23.421796083450317,
  'LightGBM_BAG_L1': 15.945202350616455,
  'RandomForestMSE_BAG_L1': 3.912400722503662,
  'CatBoost_BAG_L1': 266.118775844574,
  'ExtraTreesMSE_BAG_L1': 2.3716673851013184,
  'NeuralNetFastAI_BAG_L1': 23.719738721847534,
  'XGBoost_BAG_L1': 12.375825881958008,
  'WeightedEnsemble_L2': 0.3998401165008545,
  'LightGBMXT_BAG_L2': 4.937484264373779,
  'LightGBM_BAG_L2': 4.029627323150635,
  'RandomForestMSE_BAG_L2': 12.209646940231323,
  'CatBoost_BAG_L2': 126.80808401107788,
  'ExtraTreesMSE_BAG_L2': 2.9808349609375,
  'NeuralNetFastAI_BAG_L2': 18.725494146347046,
  'WeightedEnsemble_L3': 0.2771182060241699},
 'model_pred_times': {'KNeighborsUnif_BAG_L1': 0.015583992004394531,
  'KNeighborsDist_BAG_L1': 0.031208038330078125,
  'LightGBMXT_BAG_L1': 11.907729148864746,
  'LightGBM_BAG_L1': 2.6877601146698,
  'RandomForestMSE_BAG_L1': 0.39418792724609375,
  'CatBoost_BAG_L1': 0.14006900787353516,
  'ExtraTreesMSE_BAG_L1': 0.44112610816955566,
  'NeuralNetFastAI_BAG_L1': 0.3912618160247803,
  'XGBoost_BAG_L1': 0.7138073444366455,
  'WeightedEnsemble_L2': 0.0,
  'LightGBMXT_BAG_L2': 0.5396385192871094,
  'LightGBM_BAG_L2': 0.2413806915283203,
  'RandomForestMSE_BAG_L2': 0.4637877941131592,
  'CatBoost_BAG_L2': 0.054283857345581055,
  'ExtraTreesMSE_BAG_L2': 0.43993067741394043,
  'NeuralNetFastAI_BAG_L2': 0.30977964401245117,
  'WeightedEnsemble_L3': 0.0},
 'num_bag_folds': 8,
 'max_stack_level': 3,
 'model_hyperparams': {'KNeighborsUnif_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'KNeighborsDist_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'LightGBMXT_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'RandomForestMSE_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'CatBoost_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'ExtraTreesMSE_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'NeuralNetFastAI_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'XGBoost_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'WeightedEnsemble_L2': {'use_orig_features': False,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBMXT_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'RandomForestMSE_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'CatBoost_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'ExtraTreesMSE_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True,
   'use_child_oof': True},
  'NeuralNetFastAI_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'WeightedEnsemble_L3': {'use_orig_features': False,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True}},
 'leaderboard':                      model   score_val  pred_time_val    fit_time  \
 0      WeightedEnsemble_L3  -29.890078      17.328178  497.813932   
 1   NeuralNetFastAI_BAG_L2  -30.300083      17.032513  366.699103   
 2          CatBoost_BAG_L2  -30.497057      16.777017  474.781693   
 3          LightGBM_BAG_L2  -30.777089      16.964114  352.003236   
 4        LightGBMXT_BAG_L2  -31.196428      17.262372  352.911093   
 5     ExtraTreesMSE_BAG_L2  -31.690163      17.162664  350.954443   
 6   RandomForestMSE_BAG_L2  -31.846290      17.186521  360.183255   
 7      WeightedEnsemble_L2  -31.945469      15.874762  322.231183   
 8          LightGBM_BAG_L1  -33.887545       2.687760   15.945202   
 9          CatBoost_BAG_L1  -33.910528       0.140069  266.118776   
 10       LightGBMXT_BAG_L1  -34.000297      11.907729   23.421796   
 11          XGBoost_BAG_L1  -34.623349       0.713807   12.375826   
 12    ExtraTreesMSE_BAG_L1  -37.960508       0.441126    2.371667   
 13  RandomForestMSE_BAG_L1  -38.263675       0.394188    3.912401   
 14  NeuralNetFastAI_BAG_L1  -44.205036       0.391262   23.719739   
 15   KNeighborsDist_BAG_L1  -84.146423       0.031208    0.057342   
 16   KNeighborsUnif_BAG_L1 -101.588176       0.015584    0.050859   
 
     pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  \
 0                 0.000000           0.277118            3       True   
 1                 0.309780          18.725494            2       True   
 2                 0.054284         126.808084            2       True   
 3                 0.241381           4.029627            2       True   
 4                 0.539639           4.937484            2       True   
 5                 0.439931           2.980835            2       True   
 6                 0.463788          12.209647            2       True   
 7                 0.000000           0.399840            2       True   
 8                 2.687760          15.945202            1       True   
 9                 0.140069         266.118776            1       True   
 10               11.907729          23.421796            1       True   
 11                0.713807          12.375826            1       True   
 12                0.441126           2.371667            1       True   
 13                0.394188           3.912401            1       True   
 14                0.391262          23.719739            1       True   
 15                0.031208           0.057342            1       True   
 16                0.015584           0.050859            1       True   
 
     fit_order  
 0          17  
 1          16  
 2          14  
 3          12  
 4          11  
 5          15  
 6          13  
 7          10  
 8           4  
 9           6  
 10          3  
 11          9  
 12          7  
 13          5  
 14          8  
 15          2  
 16          1  }

predictions_new_features = predictor_new_features.predict(test,model=predictor_new_features.get_model_best())
predictions_new_features.head()

0    14.893423
1     7.717738
2     6.931653
3     7.115042
4     7.138554
Name: count, dtype: float32

# Remember to set all negative values to zero
predictions_new_features.describe()

count    6493.000000
mean      148.880478
std       124.469337
min        -0.585657
25%        54.533398
50%       119.668686
75%       207.174530
max       785.126709
Name: count, dtype: float64

predictions_new_features[predictions_new_features<0].count()

6

predictions_new_features[predictions_new_features<0]=0

submission_new_features = submission.copy(deep=True)

# Same submitting predictions
submission_new_features["count"] = predictions_new_features
submission_new_features.to_csv("submission_new_features.csv", index=False)

!kaggle competitions submit -c bike-sharing-demand -f submission_new_features.csv -m "new features"

Successfully submitted to Bike Sharing Demand

  0%|          | 0.00/194k [00:00<?, ?B/s]
  4%|4         | 8.00k/194k [01:24<32:47, 97.1B/s]
 95%|#########4| 184k/194k [01:24<00:03, 3.14kB/s]
100%|##########| 194k/194k [01:27<00:00, 2.27kB/s]

!kaggle competitions submissions -c bike-sharing-demand 
#| tail -n +1 | head -n 6

fileName                     date                 description           status    publicScore  privateScore  
---------------------------  -------------------  --------------------  --------  -----------  ------------  
submission_new_features.csv  2023-05-30 06:32:08  new features          complete  0.70588      0.70588       
submission.csv               2023-05-30 05:49:46  first raw submission  complete  1.80425      1.80425       

New Score of 0.70588

Step 6: Hyper parameter optimization

• There are many options for hyper parameter optimization.
• Options are to change the AutoGluon higher level parameters or the individual model hyperparameters.
• The hyperparameters of the models themselves that are in AutoGluon. Those need the hyperparameter and hyperparameter_tune_kwargs arguments.

time_limit = 10*60  # train various models for 10 mins
num_trials = 10  # try at most 10 different hyperparameter configurations for each type of model
search_strategy = 'auto'  #"bayes", # random # to tune hyperparameters using Bayesian optimization routine with a local scheduler

hyperparameter_tune_kwargs = {
    'num_trials': num_trials,
    'scheduler' : "ASHA", #'local', #
    'searcher': search_strategy,
}

predictor_new_hpo = TabularPredictor('count',problem_type='regression',learner_kwargs={"ignored_columns":['casual','registered']},
                             eval_metric='root_mean_squared_error').fit(train,time_limit=600,presets='best_quality',
                                                                   hyperparameter_tune_kwargs=hyperparameter_tune_kwargs)

No model was trained during hyperparameter tuning NeuralNetTorch_BAG_L2... Skipping this model.
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 29.98s of the 235.49s of remaining time.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.8223	 = Validation score   (-root_mean_squared_error)
	8.56s	 = Training   runtime
	0.22s	 = Validation runtime
Repeating k-fold bagging: 2/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 222.75s of the 222.74s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.5555	 = Validation score   (-root_mean_squared_error)
	12.48s	 = Training   runtime
	0.44s	 = Validation runtime
Repeating k-fold bagging: 3/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 209.52s of the 209.51s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.4301	 = Validation score   (-root_mean_squared_error)
	16.49s	 = Training   runtime
	0.68s	 = Validation runtime
Repeating k-fold bagging: 4/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 196.24s of the 196.23s of remaining time.
	Fitting 8 child models (S4F1 - S4F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3767	 = Validation score   (-root_mean_squared_error)
	20.28s	 = Training   runtime
	0.94s	 = Validation runtime
Repeating k-fold bagging: 5/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 183.23s of the 183.22s of remaining time.
	Fitting 8 child models (S5F1 - S5F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3831	 = Validation score   (-root_mean_squared_error)
	24.0s	 = Training   runtime
	1.13s	 = Validation runtime
Repeating k-fold bagging: 6/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 170.37s of the 170.36s of remaining time.
	Fitting 8 child models (S6F1 - S6F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3714	 = Validation score   (-root_mean_squared_error)
	27.88s	 = Training   runtime
	1.37s	 = Validation runtime
Repeating k-fold bagging: 7/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 157.21s of the 157.2s of remaining time.
	Fitting 8 child models (S7F1 - S7F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3516	 = Validation score   (-root_mean_squared_error)
	31.78s	 = Training   runtime
	1.59s	 = Validation runtime
Repeating k-fold bagging: 8/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 144.23s of the 144.22s of remaining time.
	Fitting 8 child models (S8F1 - S8F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3586	 = Validation score   (-root_mean_squared_error)
	35.57s	 = Training   runtime
	1.79s	 = Validation runtime
Repeating k-fold bagging: 9/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 130.74s of the 130.73s of remaining time.
	Fitting 8 child models (S9F1 - S9F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3815	 = Validation score   (-root_mean_squared_error)
	39.77s	 = Training   runtime
	2.03s	 = Validation runtime
Repeating k-fold bagging: 10/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 117.37s of the 117.36s of remaining time.
	Fitting 8 child models (S10F1 - S10F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3955	 = Validation score   (-root_mean_squared_error)
	43.75s	 = Training   runtime
	2.22s	 = Validation runtime
Repeating k-fold bagging: 11/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 104.16s of the 104.15s of remaining time.
	Fitting 8 child models (S11F1 - S11F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3799	 = Validation score   (-root_mean_squared_error)
	47.86s	 = Training   runtime
	2.45s	 = Validation runtime
Repeating k-fold bagging: 12/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 90.81s of the 90.8s of remaining time.
	Fitting 8 child models (S12F1 - S12F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.4001	 = Validation score   (-root_mean_squared_error)
	51.86s	 = Training   runtime
	2.64s	 = Validation runtime
Repeating k-fold bagging: 13/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 77.19s of the 77.18s of remaining time.
	Fitting 8 child models (S13F1 - S13F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3765	 = Validation score   (-root_mean_squared_error)
	55.88s	 = Training   runtime
	2.83s	 = Validation runtime
Repeating k-fold bagging: 14/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 63.8s of the 63.79s of remaining time.
	Fitting 8 child models (S14F1 - S14F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3778	 = Validation score   (-root_mean_squared_error)
	59.89s	 = Training   runtime
	3.05s	 = Validation runtime
Repeating k-fold bagging: 15/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 50.53s of the 50.52s of remaining time.
	Fitting 8 child models (S15F1 - S15F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3843	 = Validation score   (-root_mean_squared_error)
	63.89s	 = Training   runtime
	3.26s	 = Validation runtime
Repeating k-fold bagging: 16/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 36.86s of the 36.85s of remaining time.
	Fitting 8 child models (S16F1 - S16F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3761	 = Validation score   (-root_mean_squared_error)
	67.85s	 = Training   runtime
	3.49s	 = Validation runtime
Repeating k-fold bagging: 17/20
Fitting model: LightGBMLarge_BAG_L2 ... Training model for up to 23.46s of the 23.45s of remaining time.
	Fitting 8 child models (S17F1 - S17F8) | Fitting with ParallelLocalFoldFittingStrategy
	-33.3623	 = Validation score   (-root_mean_squared_error)
	71.98s	 = Training   runtime
	3.72s	 = Validation runtime
Completed 17/20 k-fold bagging repeats ...
Fitting model: WeightedEnsemble_L3 ... Training model for up to 360.0s of the 9.59s of remaining time.
	-33.3623	 = Validation score   (-root_mean_squared_error)
	0.0s	 = Training   runtime
	0.0s	 = Validation runtime
AutoGluon training complete, total runtime = 590.44s ... Best model: "WeightedEnsemble_L2"
TabularPredictor saved. To load, use: predictor = TabularPredictor.load("AutogluonModels\ag-20230531_004701\")

predictor_new_hpo.fit_summary()

*** Summary of fit() ***
Estimated performance of each model:
                             model  score_val  pred_time_val    fit_time  pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  fit_order
0              WeightedEnsemble_L2 -32.375607       3.666819  196.446225                0.000000           0.158715            2       True          4
1             LightGBMLarge_BAG_L1 -32.552075       3.557436   34.594732                3.557436          34.594732            1       True          3
2             LightGBMLarge_BAG_L2 -33.362305       7.653478  313.601118                3.721043          71.981003            2       True          5
3              WeightedEnsemble_L3 -33.362305       7.654464  313.603590                0.000986           0.002472            3       True          6
4   NeuralNetTorch_BAG_L1\6349b722 -45.199272       0.109383  161.692777                0.109383         161.692777            1       True          2
5  NeuralNetFastAI_BAG_L1\5aea9def -46.628290       0.265617   45.332606                0.265617          45.332606            1       True          1
Number of models trained: 6
Types of models trained:
{'WeightedEnsembleModel', 'StackerEnsembleModel_NNFastAiTabular', 'StackerEnsembleModel_TabularNeuralNetTorch', 'StackerEnsembleModel_LGB'}
Bagging used: True  (with 8 folds)
Multi-layer stack-ensembling used: True  (with 3 levels)
Feature Metadata (Processed):
(raw dtype, special dtypes):
('category', [])             : 3 | ['season', 'weather', 'weekday']
('float', [])                : 3 | ['temp', 'atemp', 'windspeed']
('int', [])                  : 3 | ['humidity', 'week', 'hour']
('int', ['bool'])            : 3 | ['holiday', 'workingday', 'year']
('int', ['datetime_as_int']) : 5 | ['datetime', 'datetime.year', 'datetime.month', 'datetime.day', 'datetime.dayofweek']
*** End of fit() summary ***

{'model_types': {'NeuralNetFastAI_BAG_L1\\5aea9def': 'StackerEnsembleModel_NNFastAiTabular',
  'NeuralNetTorch_BAG_L1\\6349b722': 'StackerEnsembleModel_TabularNeuralNetTorch',
  'LightGBMLarge_BAG_L1': 'StackerEnsembleModel_LGB',
  'WeightedEnsemble_L2': 'WeightedEnsembleModel',
  'LightGBMLarge_BAG_L2': 'StackerEnsembleModel_LGB',
  'WeightedEnsemble_L3': 'WeightedEnsembleModel'},
 'model_performance': {'NeuralNetFastAI_BAG_L1\\5aea9def': -46.6282896132067,
  'NeuralNetTorch_BAG_L1\\6349b722': -45.199272049199045,
  'LightGBMLarge_BAG_L1': -32.552074649850724,
  'WeightedEnsemble_L2': -32.37560661696187,
  'LightGBMLarge_BAG_L2': -33.3623048521261,
  'WeightedEnsemble_L3': -33.3623048521261},
 'model_best': 'WeightedEnsemble_L2',
 'model_paths': {'NeuralNetFastAI_BAG_L1\\5aea9def': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_004701\\models\\NeuralNetFastAI_BAG_L1\\5aea9def\\',
  'NeuralNetTorch_BAG_L1\\6349b722': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_004701\\models\\NeuralNetTorch_BAG_L1\\6349b722\\',
  'LightGBMLarge_BAG_L1': 'AutogluonModels\\ag-20230531_004701\\models\\LightGBMLarge_BAG_L1\\',
  'WeightedEnsemble_L2': 'AutogluonModels\\ag-20230531_004701\\models\\WeightedEnsemble_L2\\',
  'LightGBMLarge_BAG_L2': 'AutogluonModels\\ag-20230531_004701\\models\\LightGBMLarge_BAG_L2\\',
  'WeightedEnsemble_L3': 'AutogluonModels\\ag-20230531_004701\\models\\WeightedEnsemble_L3\\'},
 'model_fit_times': {'NeuralNetFastAI_BAG_L1\\5aea9def': 45.332605600357056,
  'NeuralNetTorch_BAG_L1\\6349b722': 161.69277715682983,
  'LightGBMLarge_BAG_L1': 34.5947322845459,
  'WeightedEnsemble_L2': 0.15871524810791016,
  'LightGBMLarge_BAG_L2': 71.98100304603577,
  'WeightedEnsemble_L3': 0.0024721622467041016},
 'model_pred_times': {'NeuralNetFastAI_BAG_L1\\5aea9def': 0.26561689376831055,
  'NeuralNetTorch_BAG_L1\\6349b722': 0.10938262939453125,
  'LightGBMLarge_BAG_L1': 3.557435989379883,
  'WeightedEnsemble_L2': 0.0,
  'LightGBMLarge_BAG_L2': 3.7210428714752197,
  'WeightedEnsemble_L3': 0.000985860824584961},
 'num_bag_folds': 8,
 'max_stack_level': 3,
 'model_hyperparams': {'NeuralNetFastAI_BAG_L1\\5aea9def': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'NeuralNetTorch_BAG_L1\\6349b722': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBMLarge_BAG_L1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'WeightedEnsemble_L2': {'use_orig_features': False,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBMLarge_BAG_L2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'WeightedEnsemble_L3': {'use_orig_features': False,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True}},
 'leaderboard':                              model  score_val  pred_time_val    fit_time  \
 0              WeightedEnsemble_L2 -32.375607       3.666819  196.446225   
 1             LightGBMLarge_BAG_L1 -32.552075       3.557436   34.594732   
 2             LightGBMLarge_BAG_L2 -33.362305       7.653478  313.601118   
 3              WeightedEnsemble_L3 -33.362305       7.654464  313.603590   
 4   NeuralNetTorch_BAG_L1\6349b722 -45.199272       0.109383  161.692777   
 5  NeuralNetFastAI_BAG_L1\5aea9def -46.628290       0.265617   45.332606   
 
    pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  \
 0                0.000000           0.158715            2       True   
 1                3.557436          34.594732            1       True   
 2                3.721043          71.981003            2       True   
 3                0.000986           0.002472            3       True   
 4                0.109383         161.692777            1       True   
 5                0.265617          45.332606            1       True   
 
    fit_order  
 0          4  
 1          3  
 2          5  
 3          6  
 4          2  
 5          1  }

predictions_new_features_hpo = predictor_new_hpo.predict(test,model=predictor_new_hpo.get_model_best())
predictions_new_features_hpo.head()

0    13.315242
1    -1.718998
2    -4.141519
3     0.576120
4     0.718507
Name: count, dtype: float32

# Remember to set all negative values to zero
predictions_new_features_hpo.describe()

count    6493.000000
mean      191.578339
std       172.726730
min        -6.694787
25%        45.578114
50%       150.683228
75%       284.875244
max       876.015808
Name: count, dtype: float64

predictions_new_features_hpo[predictions_new_features_hpo<0].count()

58

predictions_new_features_hpo[predictions_new_features_hpo<0]=0

submission_new_hpo = submission.copy(deep=True)

# Same submitting predictions
submission_new_hpo["count"] = predictions_new_features_hpo
submission_new_hpo.to_csv("submission_new_hpo.csv", index=False)

!kaggle competitions submit -c bike-sharing-demand -f submission_new_hpo.csv -m "new features with hyperparameters"

Successfully submitted to Bike Sharing Demand

  0%|          | 0.00/194k [00:00<?, ?B/s]
  4%|4         | 8.00k/194k [01:24<32:48, 96.9B/s]
 95%|#########4| 184k/194k [01:24<00:03, 3.13kB/s]
100%|##########| 194k/194k [01:26<00:00, 2.29kB/s]

!kaggle competitions submissions -c bike-sharing-demand 
#| tail -n +1 | head -n 6

fileName                     date                 description                        status    publicScore  privateScore  
---------------------------  -------------------  ---------------------------------  --------  -----------  ------------  
submission_new_hpo.csv       2023-05-31 00:59:18  new features with hyperparameters  complete  0.49844      0.49844       
submission_new_features.csv  2023-05-30 06:32:08  new features                       complete  0.70588      0.70588       
submission.csv               2023-05-30 05:49:46  first raw submission               complete  1.80425      1.80425       

New Score of 0.49844

nn_options = {  # specifies non-default hyperparameter values for neural network models
    'num_epochs': 10,  # number of training epochs (controls training time of NN models)
    'learning_rate': ag.space.Real(1e-3, 1e-2, default=5e-3, log=True),  # learning rate used in training (real-valued hyperparameter searched on log-scale)
    'activation': ag.space.Categorical('relu', 'softrelu', 'tanh'),  # activation function used in NN (categorical hyperparameter, default = first entry)
    'layers': ag.space.Categorical([100],[200, 100]),  # each choice for categorical hyperparameter 'layers' corresponds to list of sizes for each NN layer to use
    'dropout_prob': ag.space.Real(0.0, 0.5, default=0.1),  # dropout probability (real-valued hyperparameter)
}

gbm_options = {  # specifies non-default hyperparameter values for lightGBM gradient boosted trees
    'num_boost_round': 80,  # number of boosting rounds (controls training time of GBM models)
    'num_leaves': ag.space.Int(lower=10, upper=50, default=20),  # number of leaves in trees (integer hyperparameter)
}

hyperparameters = {  # hyperparameters of each model type
                   'GBM': gbm_options,
                   'NN_TORCH': nn_options,
                  } 

time_limit = 10*60  # train various models for ~2 min
num_trials = 10  # try at most 5 different hyperparameter configurations for each type of model
search_strategy = 'auto'  # to tune hyperparameters using Bayesian optimization routine with a local scheduler

hyperparameter_tune_kwargs = {
    'num_trials': num_trials,
    'scheduler' : 'local',
    'searcher': search_strategy,
}

predictor_new_hpo1 = TabularPredictor('count',problem_type='regression',learner_kwargs={"ignored_columns":['casual','registered']},
                             eval_metric='root_mean_squared_error').fit(train,time_limit=time_limit,presets='best_quality',
                                                                   hyperparameters=hyperparameters, hyperparameter_tune_kwargs=hyperparameter_tune_kwargs)

No path specified. Models will be saved in: "AutogluonModels\ag-20230531_025623\"
Presets specified: ['best_quality']
Warning: hyperparameter tuning is currently experimental and may cause the process to hang.
Stack configuration (auto_stack=True): num_stack_levels=1, num_bag_folds=8, num_bag_sets=20
Beginning AutoGluon training ... Time limit = 600s
AutoGluon will save models to "AutogluonModels\ag-20230531_025623\"
AutoGluon Version:  0.7.0
Python Version:     3.8.16
Operating System:   Windows
Platform Machine:   AMD64
Platform Version:   10.0.19045
Train Data Rows:    10886
Train Data Columns: 15
Label Column: count
Preprocessing data ...
Using Feature Generators to preprocess the data ...
Dropping user-specified ignored columns: ['casual', 'registered']
Fitting AutoMLPipelineFeatureGenerator...
	Available Memory:                    8304.23 MB
	Train Data (Original)  Memory Usage: 0.83 MB (0.0% of available memory)
	Inferring data type of each feature based on column values. Set feature_metadata_in to manually specify special dtypes of the features.
	Stage 1 Generators:
		Fitting AsTypeFeatureGenerator...
			Note: Converting 3 features to boolean dtype as they only contain 2 unique values.
	Stage 2 Generators:
		Fitting FillNaFeatureGenerator...
	Stage 3 Generators:
		Fitting IdentityFeatureGenerator...
		Fitting CategoryFeatureGenerator...
			Fitting CategoryMemoryMinimizeFeatureGenerator...
		Fitting DatetimeFeatureGenerator...
	Stage 4 Generators:
		Fitting DropUniqueFeatureGenerator...
	Types of features in original data (raw dtype, special dtypes):
		('category', []) : 4 | ['season', 'weather', 'year', 'weekday']
		('datetime', []) : 1 | ['datetime']
		('float', [])    : 3 | ['temp', 'atemp', 'windspeed']
		('int', [])      : 5 | ['holiday', 'workingday', 'humidity', 'week', 'hour']
	Types of features in processed data (raw dtype, special dtypes):
		('category', [])             : 3 | ['season', 'weather', 'weekday']
		('float', [])                : 3 | ['temp', 'atemp', 'windspeed']
		('int', [])                  : 3 | ['humidity', 'week', 'hour']
		('int', ['bool'])            : 3 | ['holiday', 'workingday', 'year']
		('int', ['datetime_as_int']) : 5 | ['datetime', 'datetime.year', 'datetime.month', 'datetime.day', 'datetime.dayofweek']
	0.1s = Fit runtime
	13 features in original data used to generate 17 features in processed data.
	Train Data (Processed) Memory Usage: 1.02 MB (0.0% of available memory)
Data preprocessing and feature engineering runtime = 0.12s ...
AutoGluon will gauge predictive performance using evaluation metric: 'root_mean_squared_error'
	This metric's sign has been flipped to adhere to being higher_is_better. The metric score can be multiplied by -1 to get the metric value.
	To change this, specify the eval_metric parameter of Predictor()
AutoGluon will fit 2 stack levels (L1 to L2) ...
	WARNING: "NN" model has been deprecated in v0.4.0 and renamed to "NN_MXNET". Starting in v0.6.0, specifying "NN" or "NN_MXNET" will raise an exception. Consider instead specifying "NN_TORCH".
Fitting 2 L1 models ...
Hyperparameter tuning model: LightGBM_BAG_L1 ... Tuning model for up to 179.92s of the 599.88s of remaining time.

  0%|          | 0/10 [00:00<?, ?it/s]

	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
Fitted model: LightGBM_BAG_L1\T1 ...
	-48.1213	 = Validation score   (-root_mean_squared_error)
	10.23s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T2 ...
	-48.8559	 = Validation score   (-root_mean_squared_error)
	11.31s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T3 ...
	-41.4635	 = Validation score   (-root_mean_squared_error)
	11.41s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T4 ...
	-140.4194	 = Validation score   (-root_mean_squared_error)
	11.24s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T5 ...
	-52.1338	 = Validation score   (-root_mean_squared_error)
	11.52s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T6 ...
	-123.4752	 = Validation score   (-root_mean_squared_error)
	11.35s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T7 ...
	-48.7354	 = Validation score   (-root_mean_squared_error)
	11.02s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T8 ...
	-37.9529	 = Validation score   (-root_mean_squared_error)
	11.21s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T9 ...
	-131.3383	 = Validation score   (-root_mean_squared_error)
	11.13s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T10 ...
	-39.8167	 = Validation score   (-root_mean_squared_error)
	11.27s	 = Training   runtime
	0.0s	 = Validation runtime
Hyperparameter tuning model: NeuralNetMXNet_BAG_L1 ... Tuning model for up to 179.92s of the 487.95s of remaining time.

  0%|          | 0/10 [00:00<?, ?it/s]

	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=31724, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=31724, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=31724, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=31724, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:25,251	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:25,252	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:25,252	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=35524, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=35524, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:25,252	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=30484, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=30484, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:25,252	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:25,267	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:25,273	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=11948, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=11948, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=11948, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=11948, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:35,031	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=21156, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=21156, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:35,037	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=16048, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=16048, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:35,044	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:35,052	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:35,057	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:35,058	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:35,065	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=25204, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=25204, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=25204, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=25204, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:44,077	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:44,082	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:44,087	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:44,092	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:44,096	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:44,103	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:44,106	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=34432, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=34432, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=34432, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=34432, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:53,474	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=33764, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=33764, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:53,477	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:53,481	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=18588, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=18588, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:53,481	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=26948, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=26948, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
2023-05-31 07:58:53,497	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=35148, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=35148, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:58:53,500	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:58:53,502	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=18052, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=18052, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
ray::_ray_fit() (pid=34824, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=34824, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=34824, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=34824, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:59:03,123	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:03,129	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
2023-05-31 07:59:03,146	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:03,149	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:03,155	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:03,160	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:03,165	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
ray::_ray_fit() (pid=15848, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=15848, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=15848, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=15848, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:59:11,996	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:12,005	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:12,009	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:12,014	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:12,017	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:12,021	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
2023-05-31 07:59:12,040	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
ray::_ray_fit() (pid=35588, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=35588, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=35588, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=35588, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:59:21,215	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:21,219	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:21,225	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:21,231	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:21,239	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:21,242	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:21,272	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=11756, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=11756, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=11756, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=11756, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:59:30,477	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:30,483	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:30,488	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:30,490	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:30,499	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:30,502	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:30,507	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=21964, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=21964, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=21964, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=21964, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 07:59:39,565	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:39,583	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:39,588	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:39,594	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:39,598	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:39,602	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:39,605	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=27000, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=27000, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=27000, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=27000, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
No model was trained during hyperparameter tuning NeuralNetMXNet_BAG_L1... Skipping this model.
Completed 1/20 k-fold bagging repeats ...
2023-05-31 07:59:48,948	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:48,948	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:48,948	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:48,963	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:48,963	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:48,963	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 07:59:48,963	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
Fitting model: WeightedEnsemble_L2 ... Training model for up to 360.0s of the 394.53s of remaining time.
	-37.5413	 = Validation score   (-root_mean_squared_error)
	0.33s	 = Training   runtime
	0.0s	 = Validation runtime
	WARNING: "NN" model has been deprecated in v0.4.0 and renamed to "NN_MXNET". Starting in v0.6.0, specifying "NN" or "NN_MXNET" will raise an exception. Consider instead specifying "NN_TORCH".
Fitting 2 L2 models ...
Hyperparameter tuning model: LightGBM_BAG_L2 ... Tuning model for up to 177.38s of the 394.17s of remaining time.

  0%|          | 0/10 [00:00<?, ?it/s]

	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
Fitted model: LightGBM_BAG_L2\T1 ...
	-37.2839	 = Validation score   (-root_mean_squared_error)
	11.08s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T2 ...
	-36.9719	 = Validation score   (-root_mean_squared_error)
	11.68s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T3 ...
	-37.0125	 = Validation score   (-root_mean_squared_error)
	11.56s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T4 ...
	-115.2035	 = Validation score   (-root_mean_squared_error)
	11.2s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T5 ...
	-38.6166	 = Validation score   (-root_mean_squared_error)
	11.37s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T6 ...
	-111.8066	 = Validation score   (-root_mean_squared_error)
	11.08s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T7 ...
	-36.9637	 = Validation score   (-root_mean_squared_error)
	11.01s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T8 ...
	-36.5962	 = Validation score   (-root_mean_squared_error)
	11.24s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T9 ...
	-103.2097	 = Validation score   (-root_mean_squared_error)
	11.07s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T10 ...
	-36.7172	 = Validation score   (-root_mean_squared_error)
	11.18s	 = Training   runtime
	0.0s	 = Validation runtime
Hyperparameter tuning model: NeuralNetMXNet_BAG_L2 ... Tuning model for up to 177.38s of the 281.45s of remaining time.

  0%|          | 0/10 [00:00<?, ?it/s]

	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=15272, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=15272, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=15272, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=15272, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:01:52,463	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=29056, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=29056, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:01:52,468	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=24748, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=24748, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:01:52,472	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=12428, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=12428, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:01:52,475	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=35860, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=35860, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:01:52,478	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:01:52,482	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:01:52,485	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=14068, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=14068, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=14068, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=14068, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:03,281	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=19004, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=19004, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:03,312	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:03,327	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:03,333	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:03,338	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:03,343	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:03,347	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=15872, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=15872, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=15872, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=15872, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:12,750	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=6252, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=6252, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:12,754	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:12,757	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:12,761	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:12,765	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:12,770	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:12,775	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=20268, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=20268, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=20268, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=20268, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:21,907	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=24276, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=24276, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:21,918	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:21,921	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:21,921	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:21,929	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:21,934	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:21,938	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=21556, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=21556, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=21556, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=21556, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:31,743	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=21244, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=21244, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:31,754	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:31,759	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:31,764	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:31,769	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:31,773	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:31,777	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=16464, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=16464, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=16464, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=16464, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:40,925	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:40,929	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=15708, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=15708, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:40,932	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:40,935	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:40,941	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:40,945	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:40,949	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=20376, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=20376, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=20376, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=20376, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:49,869	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:49,869	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:49,869	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:49,869	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:49,885	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:49,885	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:49,885	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=29528, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=29528, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=29528, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=29528, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:02:58,726	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:58,733	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:58,733	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:58,740	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:58,747	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:58,747	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:02:58,754	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=16200, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=16200, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=16200, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=16200, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:03:07,850	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:03:07,853	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:03:07,857	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:03:07,858	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): ray::_ray_fit() (pid=10052, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=10052, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
2023-05-31 08:03:07,866	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:03:07,871	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:03:07,875	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
ray::_ray_fit() (pid=15076, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=15076, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 43, in model_trial
    model = fit_and_save_model(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\model_trial.py", line 101, in fit_and_save_model
    model.fit(**fit_args, time_limit=time_left)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 154, in _fit
    return super()._fit(X=X, y=y, time_limit=time_limit, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 248, in _fit
    self._fit_folds(X=X, y=y, model_base=model_base, X_pseudo=X_pseudo, y_pseudo=y_pseudo,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 540, in _fit_folds
    fold_fitting_strategy.after_all_folds_scheduled()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 537, in after_all_folds_scheduled
    raise processed_exception
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 505, in after_all_folds_scheduled
    time_end_fit, predict_time, predict_1_time = self.ray.get(finished)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\_private\worker.py", line 2309, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ImportError): ray::_ray_fit() (pid=15076, ip=127.0.0.1)
ModuleNotFoundError: No module named 'mxnet'

During handling of the above exception, another exception occurred:

ray::_ray_fit() (pid=15076, ip=127.0.0.1)
  File "python\ray\_raylet.pyx", line 823, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 875, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 830, in ray._raylet.execute_task
  File "python\ray\_raylet.pyx", line 834, in ray._raylet.execute_task
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\fold_fitting_strategy.py", line 374, in _ray_fit
    fold_model.fit(X=X_fold, y=y_fold, X_val=X_val_fold, y_val=y_val_fold,
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 703, in fit
    out = self._fit(**kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\tabular\models\tabular_nn\mxnet\tabular_nn_mxnet.py", line 135, in _fit
    try_import_mxnet()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\utils\try_import.py", line 49, in try_import_mxnet
    raise ImportError(
ImportError: Unable to import dependency mxnet. A quick tip is to install via `pip install mxnet --upgrade`, or `pip install mxnet_cu101 --upgrade`
No model was trained during hyperparameter tuning NeuralNetMXNet_BAG_L2... Skipping this model.
Completed 1/20 k-fold bagging repeats ...
2023-05-31 08:03:17,113	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:03:17,117	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:03:17,121	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
Fitting model: WeightedEnsemble_L3 ... Training model for up to 360.0s of the 186.45s of remaining time.
2023-05-31 08:03:17,128	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:03:17,132	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:03:17,137	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
2023-05-31 08:03:17,142	ERROR worker.py:400 -- Unhandled error (suppress with 'RAY_IGNORE_UNHANDLED_ERRORS=1'): The worker died unexpectedly while executing this task. Check python-core-worker-*.log files for more information.
	-36.4283	 = Validation score   (-root_mean_squared_error)
	0.31s	 = Training   runtime
	0.0s	 = Validation runtime
AutoGluon training complete, total runtime = 413.92s ... Best model: "WeightedEnsemble_L3"
TabularPredictor saved. To load, use: predictor = TabularPredictor.load("AutogluonModels\ag-20230531_025623\")

predictor_new_hpo1.fit_summary()

*** Summary of fit() ***
Estimated performance of each model:
                  model   score_val  pred_time_val    fit_time  pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  fit_order
0   WeightedEnsemble_L3  -36.428313       0.001001  146.086720                0.000000           0.305657            3       True         22
1    LightGBM_BAG_L2\T8  -36.596210       0.001001  122.927084                0.000000          11.239582            2       True         19
2   LightGBM_BAG_L2\T10  -36.717208       0.001001  122.865482                0.000000          11.177980            2       True         21
3    LightGBM_BAG_L2\T7  -36.963696       0.001001  122.702333                0.000000          11.014831            2       True         18
4    LightGBM_BAG_L2\T2  -36.971947       0.001001  123.363501                0.000000          11.675999            2       True         13
5    LightGBM_BAG_L2\T3  -37.012459       0.001001  123.246503                0.000000          11.559000            2       True         14
6    LightGBM_BAG_L2\T1  -37.283893       0.001001  122.771036                0.000000          11.083534            2       True         12
7   WeightedEnsemble_L2  -37.541253       0.000000   22.808565                0.000000           0.326270            2       True         11
8    LightGBM_BAG_L1\T8  -37.952891       0.000000   11.213756                0.000000          11.213756            1       True          8
9    LightGBM_BAG_L2\T5  -38.616601       0.001001  123.054728                0.000000          11.367225            2       True         16
10  LightGBM_BAG_L1\T10  -39.816719       0.000000   11.268540                0.000000          11.268540            1       True         10
11   LightGBM_BAG_L1\T3  -41.463544       0.000000   11.409003                0.000000          11.409003            1       True          3
12   LightGBM_BAG_L1\T1  -48.121313       0.000000   10.226465                0.000000          10.226465            1       True          1
13   LightGBM_BAG_L1\T7  -48.735404       0.000000   11.016189                0.000000          11.016189            1       True          7
14   LightGBM_BAG_L1\T2  -48.855901       0.000000   11.310180                0.000000          11.310180            1       True          2
15   LightGBM_BAG_L1\T5  -52.133844       0.000000   11.518472                0.000000          11.518472            1       True          5
16   LightGBM_BAG_L2\T9 -103.209737       0.001001  122.754920                0.000000          11.067417            2       True         20
17   LightGBM_BAG_L2\T6 -111.806629       0.001001  122.767490                0.000000          11.079988            2       True         17
18   LightGBM_BAG_L2\T4 -115.203453       0.001001  122.883715                0.000000          11.196213            2       True         15
19   LightGBM_BAG_L1\T6 -123.475210       0.000000   11.351787                0.000000          11.351787            1       True          6
20   LightGBM_BAG_L1\T9 -131.338336       0.000000   11.133766                0.000000          11.133766            1       True          9
21   LightGBM_BAG_L1\T4 -140.419440       0.001001   11.239344                0.001001          11.239344            1       True          4
Number of models trained: 22
Types of models trained:
{'StackerEnsembleModel_LGB', 'WeightedEnsembleModel'}
Bagging used: True  (with 8 folds)
Multi-layer stack-ensembling used: True  (with 3 levels)
Feature Metadata (Processed):
(raw dtype, special dtypes):
('category', [])             : 3 | ['season', 'weather', 'weekday']
('float', [])                : 3 | ['temp', 'atemp', 'windspeed']
('int', [])                  : 3 | ['humidity', 'week', 'hour']
('int', ['bool'])            : 3 | ['holiday', 'workingday', 'year']
('int', ['datetime_as_int']) : 5 | ['datetime', 'datetime.year', 'datetime.month', 'datetime.day', 'datetime.dayofweek']
*** End of fit() summary ***

{'model_types': {'LightGBM_BAG_L1\\T1': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T2': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T3': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T4': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T5': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T6': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T7': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T8': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T9': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T10': 'StackerEnsembleModel_LGB',
  'WeightedEnsemble_L2': 'WeightedEnsembleModel',
  'LightGBM_BAG_L2\\T1': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T2': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T3': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T4': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T5': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T6': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T7': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T8': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T9': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T10': 'StackerEnsembleModel_LGB',
  'WeightedEnsemble_L3': 'WeightedEnsembleModel'},
 'model_performance': {'LightGBM_BAG_L1\\T1': -48.12131286915449,
  'LightGBM_BAG_L1\\T2': -48.85590120876569,
  'LightGBM_BAG_L1\\T3': -41.46354388112384,
  'LightGBM_BAG_L1\\T4': -140.41943976016316,
  'LightGBM_BAG_L1\\T5': -52.13384437355743,
  'LightGBM_BAG_L1\\T6': -123.47521008865463,
  'LightGBM_BAG_L1\\T7': -48.735403708143814,
  'LightGBM_BAG_L1\\T8': -37.95289071380219,
  'LightGBM_BAG_L1\\T9': -131.3383358294307,
  'LightGBM_BAG_L1\\T10': -39.816719373139044,
  'WeightedEnsemble_L2': -37.541252816500524,
  'LightGBM_BAG_L2\\T1': -37.28389313469878,
  'LightGBM_BAG_L2\\T2': -36.97194684554864,
  'LightGBM_BAG_L2\\T3': -37.01245930973991,
  'LightGBM_BAG_L2\\T4': -115.20345324732774,
  'LightGBM_BAG_L2\\T5': -38.616601100504866,
  'LightGBM_BAG_L2\\T6': -111.80662861630574,
  'LightGBM_BAG_L2\\T7': -36.9636959240076,
  'LightGBM_BAG_L2\\T8': -36.59621044633373,
  'LightGBM_BAG_L2\\T9': -103.20973745528875,
  'LightGBM_BAG_L2\\T10': -36.71720837197882,
  'WeightedEnsemble_L3': -36.42831329448963},
 'model_best': 'WeightedEnsemble_L3',
 'model_paths': {'LightGBM_BAG_L1\\T1': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L1\\T1\\',
  'LightGBM_BAG_L1\\T2': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L1\\T2\\',
  'LightGBM_BAG_L1\\T3': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L1\\T3\\',
  'LightGBM_BAG_L1\\T4': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L1\\T4\\',
  'LightGBM_BAG_L1\\T5': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L1\\T5\\',
  'LightGBM_BAG_L1\\T6': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L1\\T6\\',
  'LightGBM_BAG_L1\\T7': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L1\\T7\\',
  'LightGBM_BAG_L1\\T8': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L1\\T8\\',
  'LightGBM_BAG_L1\\T9': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L1\\T9\\',
  'LightGBM_BAG_L1\\T10': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L1\\T10\\',
  'WeightedEnsemble_L2': 'AutogluonModels\\ag-20230531_025623\\models\\WeightedEnsemble_L2\\',
  'LightGBM_BAG_L2\\T1': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L2\\T1\\',
  'LightGBM_BAG_L2\\T2': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L2\\T2\\',
  'LightGBM_BAG_L2\\T3': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L2\\T3\\',
  'LightGBM_BAG_L2\\T4': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L2\\T4\\',
  'LightGBM_BAG_L2\\T5': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L2\\T5\\',
  'LightGBM_BAG_L2\\T6': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L2\\T6\\',
  'LightGBM_BAG_L2\\T7': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L2\\T7\\',
  'LightGBM_BAG_L2\\T8': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L2\\T8\\',
  'LightGBM_BAG_L2\\T9': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L2\\T9\\',
  'LightGBM_BAG_L2\\T10': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_025623\\models\\LightGBM_BAG_L2\\T10\\',
  'WeightedEnsemble_L3': 'AutogluonModels\\ag-20230531_025623\\models\\WeightedEnsemble_L3\\'},
 'model_fit_times': {'LightGBM_BAG_L1\\T1': 10.226464986801147,
  'LightGBM_BAG_L1\\T2': 11.310179948806763,
  'LightGBM_BAG_L1\\T3': 11.409003496170044,
  'LightGBM_BAG_L1\\T4': 11.239344120025635,
  'LightGBM_BAG_L1\\T5': 11.518471717834473,
  'LightGBM_BAG_L1\\T6': 11.351787090301514,
  'LightGBM_BAG_L1\\T7': 11.016189098358154,
  'LightGBM_BAG_L1\\T8': 11.21375584602356,
  'LightGBM_BAG_L1\\T9': 11.133766412734985,
  'LightGBM_BAG_L1\\T10': 11.268539667129517,
  'WeightedEnsemble_L2': 0.32626986503601074,
  'LightGBM_BAG_L2\\T1': 11.083534002304077,
  'LightGBM_BAG_L2\\T2': 11.67599868774414,
  'LightGBM_BAG_L2\\T3': 11.559000253677368,
  'LightGBM_BAG_L2\\T4': 11.196212768554688,
  'LightGBM_BAG_L2\\T5': 11.367225170135498,
  'LightGBM_BAG_L2\\T6': 11.07998776435852,
  'LightGBM_BAG_L2\\T7': 11.014830827713013,
  'LightGBM_BAG_L2\\T8': 11.239581823348999,
  'LightGBM_BAG_L2\\T9': 11.06741738319397,
  'LightGBM_BAG_L2\\T10': 11.177979946136475,
  'WeightedEnsemble_L3': 0.30565690994262695},
 'model_pred_times': {'LightGBM_BAG_L1\\T1': 0.0,
  'LightGBM_BAG_L1\\T2': 0.0,
  'LightGBM_BAG_L1\\T3': 0.0,
  'LightGBM_BAG_L1\\T4': 0.0010008811950683594,
  'LightGBM_BAG_L1\\T5': 0.0,
  'LightGBM_BAG_L1\\T6': 0.0,
  'LightGBM_BAG_L1\\T7': 0.0,
  'LightGBM_BAG_L1\\T8': 0.0,
  'LightGBM_BAG_L1\\T9': 0.0,
  'LightGBM_BAG_L1\\T10': 0.0,
  'WeightedEnsemble_L2': 0.0,
  'LightGBM_BAG_L2\\T1': 0.0,
  'LightGBM_BAG_L2\\T2': 0.0,
  'LightGBM_BAG_L2\\T3': 0.0,
  'LightGBM_BAG_L2\\T4': 0.0,
  'LightGBM_BAG_L2\\T5': 0.0,
  'LightGBM_BAG_L2\\T6': 0.0,
  'LightGBM_BAG_L2\\T7': 0.0,
  'LightGBM_BAG_L2\\T8': 0.0,
  'LightGBM_BAG_L2\\T9': 0.0,
  'LightGBM_BAG_L2\\T10': 0.0,
  'WeightedEnsemble_L3': 0.0},
 'num_bag_folds': 8,
 'max_stack_level': 3,
 'model_hyperparams': {'LightGBM_BAG_L1\\T1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T3': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T4': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T5': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T6': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T7': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T8': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T9': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T10': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'WeightedEnsemble_L2': {'use_orig_features': False,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T3': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T4': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T5': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T6': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T7': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T8': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T9': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T10': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'WeightedEnsemble_L3': {'use_orig_features': False,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True}},
 'leaderboard':                   model   score_val  pred_time_val    fit_time  \
 0   WeightedEnsemble_L3  -36.428313       0.001001  146.086720   
 1    LightGBM_BAG_L2\T8  -36.596210       0.001001  122.927084   
 2   LightGBM_BAG_L2\T10  -36.717208       0.001001  122.865482   
 3    LightGBM_BAG_L2\T7  -36.963696       0.001001  122.702333   
 4    LightGBM_BAG_L2\T2  -36.971947       0.001001  123.363501   
 5    LightGBM_BAG_L2\T3  -37.012459       0.001001  123.246503   
 6    LightGBM_BAG_L2\T1  -37.283893       0.001001  122.771036   
 7   WeightedEnsemble_L2  -37.541253       0.000000   22.808565   
 8    LightGBM_BAG_L1\T8  -37.952891       0.000000   11.213756   
 9    LightGBM_BAG_L2\T5  -38.616601       0.001001  123.054728   
 10  LightGBM_BAG_L1\T10  -39.816719       0.000000   11.268540   
 11   LightGBM_BAG_L1\T3  -41.463544       0.000000   11.409003   
 12   LightGBM_BAG_L1\T1  -48.121313       0.000000   10.226465   
 13   LightGBM_BAG_L1\T7  -48.735404       0.000000   11.016189   
 14   LightGBM_BAG_L1\T2  -48.855901       0.000000   11.310180   
 15   LightGBM_BAG_L1\T5  -52.133844       0.000000   11.518472   
 16   LightGBM_BAG_L2\T9 -103.209737       0.001001  122.754920   
 17   LightGBM_BAG_L2\T6 -111.806629       0.001001  122.767490   
 18   LightGBM_BAG_L2\T4 -115.203453       0.001001  122.883715   
 19   LightGBM_BAG_L1\T6 -123.475210       0.000000   11.351787   
 20   LightGBM_BAG_L1\T9 -131.338336       0.000000   11.133766   
 21   LightGBM_BAG_L1\T4 -140.419440       0.001001   11.239344   
 
     pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  \
 0                 0.000000           0.305657            3       True   
 1                 0.000000          11.239582            2       True   
 2                 0.000000          11.177980            2       True   
 3                 0.000000          11.014831            2       True   
 4                 0.000000          11.675999            2       True   
 5                 0.000000          11.559000            2       True   
 6                 0.000000          11.083534            2       True   
 7                 0.000000           0.326270            2       True   
 8                 0.000000          11.213756            1       True   
 9                 0.000000          11.367225            2       True   
 10                0.000000          11.268540            1       True   
 11                0.000000          11.409003            1       True   
 12                0.000000          10.226465            1       True   
 13                0.000000          11.016189            1       True   
 14                0.000000          11.310180            1       True   
 15                0.000000          11.518472            1       True   
 16                0.000000          11.067417            2       True   
 17                0.000000          11.079988            2       True   
 18                0.000000          11.196213            2       True   
 19                0.000000          11.351787            1       True   
 20                0.000000          11.133766            1       True   
 21                0.001001          11.239344            1       True   
 
     fit_order  
 0          22  
 1          19  
 2          21  
 3          18  
 4          13  
 5          14  
 6          12  
 7          11  
 8           8  
 9          16  
 10         10  
 11          3  
 12          1  
 13          7  
 14          2  
 15          5  
 16         20  
 17         17  
 18         15  
 19          6  
 20          9  
 21          4  }

predictions_new_features_hpo1 = predictor_new_hpo1.predict(test,model=predictor_new_hpo1.get_model_best())
predictions_new_features_hpo1.describe()

count    6493.000000
mean      190.777222
std       174.822235
min         4.802301
25%        46.602318
50%       148.788101
75%       284.207275
max       875.185486
Name: count, dtype: float64

predictions_new_features_hpo1[predictions_new_features_hpo1<0].count()

0

predictions_new_features_hpo1[predictions_new_features_hpo1<0]=0

submission_new_hpo1 = submission.copy(deep=True)

# Same submitting predictions
submission_new_hpo1["count"] = predictions_new_features_hpo1
submission_new_hpo1.to_csv("submission_new_hpo1.csv", index=False)

!kaggle competitions submit -c bike-sharing-demand -f submission_new_hpo1.csv -m "new features with hyperparameters1"

Successfully submitted to Bike Sharing Demand

  0%|          | 0.00/194k [00:00<?, ?B/s]
  4%|4         | 8.00k/194k [00:00<00:05, 37.0kB/s]
 95%|#########4| 184k/194k [00:00<00:00, 726kB/s]  
100%|##########| 194k/194k [00:04<00:00, 41.4kB/s]

!kaggle competitions submissions -c bike-sharing-demand 
#| tail -n +1 | head -n 6

fileName                     date                 description                         status    publicScore  privateScore  
---------------------------  -------------------  ----------------------------------  --------  -----------  ------------  
submission_new_hpo1.csv      2023-05-31 03:08:31  new features with hyperparameters1  complete  0.46803      0.46803       
submission_new_hpo.csv       2023-05-31 01:32:59                                      complete  0.49844      0.49844       
submission_new_hpo.csv       2023-05-31 00:59:18  new features with hyperparameters   complete  0.49844      0.49844       
submission_new_features.csv  2023-05-30 06:32:08  new features                        complete  0.70588      0.70588       
submission.csv               2023-05-30 05:49:46  first raw submission                complete  1.80425      1.80425       

New Score of 0.46803

nn_options = {  # specifies non-default hyperparameter values for neural network models
    'num_epochs': ag.space.Int(lower=8, upper=20, default=10),  # number of training epochs (controls training time of NN models)
    'learning_rate': ag.space.Real(1e-3, 1e-2, default=5e-3, log=True),  # learning rate used in training (real-valued hyperparameter searched on log-scale)
    'activation': ag.space.Categorical('relu', 'softrelu', 'tanh'),  # activation function used in NN (categorical hyperparameter, default = first entry)
    'layers': ag.space.Categorical([100],[1000],[200, 100]),  # each choice for categorical hyperparameter 'layers' corresponds to list of sizes for each NN layer to use
    'dropout_prob': ag.space.Real(0.0, 0.5, default=0.1),  # dropout probability (real-valued hyperparameter)
}

gbm_options = {  # specifies non-default hyperparameter values for lightGBM gradient boosted trees
    'num_boost_round': 80,  # number of boosting rounds (controls training time of GBM models)
    'num_leaves': ag.space.Int(lower=10, upper=50, default=20),  # number of leaves in trees (integer hyperparameter)
}

hyperparameters = {  # hyperparameters of each model type
                   'GBM': gbm_options,
                   'NN_TORCH': nn_options,
                  } 

time_limit = 10*60  # train various models for ~2 min
num_trials = 10  # try at most 5 different hyperparameter configurations for each type of model
search_strategy = 'auto'  # to tune hyperparameters using Bayesian optimization routine with a local scheduler

hyperparameter_tune_kwargs = {
    'num_trials': num_trials,
    'scheduler' : 'local',
    'searcher': search_strategy,
}

predictor_new_hpo2 = TabularPredictor('count',problem_type='regression',learner_kwargs={"ignored_columns":['casual','registered']},
                             eval_metric='root_mean_squared_error').fit(train,time_limit=time_limit,presets='best_quality',
                                                               hyperparameters=hyperparameters,
                                                               hyperparameter_tune_kwargs=hyperparameter_tune_kwargs)

No path specified. Models will be saved in: "AutogluonModels\ag-20230531_043337\"
Presets specified: ['best_quality']
Warning: hyperparameter tuning is currently experimental and may cause the process to hang.
Stack configuration (auto_stack=True): num_stack_levels=1, num_bag_folds=8, num_bag_sets=20
Beginning AutoGluon training ... Time limit = 600s
AutoGluon will save models to "AutogluonModels\ag-20230531_043337\"
AutoGluon Version:  0.7.0
Python Version:     3.8.16
Operating System:   Windows
Platform Machine:   AMD64
Platform Version:   10.0.19045
Train Data Rows:    10886
Train Data Columns: 15
Label Column: count
Preprocessing data ...
Using Feature Generators to preprocess the data ...
Dropping user-specified ignored columns: ['casual', 'registered']
Fitting AutoMLPipelineFeatureGenerator...
	Available Memory:                    6915.38 MB
	Train Data (Original)  Memory Usage: 0.83 MB (0.0% of available memory)
	Inferring data type of each feature based on column values. Set feature_metadata_in to manually specify special dtypes of the features.
	Stage 1 Generators:
		Fitting AsTypeFeatureGenerator...
			Note: Converting 3 features to boolean dtype as they only contain 2 unique values.
	Stage 2 Generators:
		Fitting FillNaFeatureGenerator...
	Stage 3 Generators:
		Fitting IdentityFeatureGenerator...
		Fitting CategoryFeatureGenerator...
			Fitting CategoryMemoryMinimizeFeatureGenerator...
		Fitting DatetimeFeatureGenerator...
	Stage 4 Generators:
		Fitting DropUniqueFeatureGenerator...
	Types of features in original data (raw dtype, special dtypes):
		('category', []) : 4 | ['season', 'weather', 'year', 'weekday']
		('datetime', []) : 1 | ['datetime']
		('float', [])    : 3 | ['temp', 'atemp', 'windspeed']
		('int', [])      : 5 | ['holiday', 'workingday', 'humidity', 'week', 'hour']
	Types of features in processed data (raw dtype, special dtypes):
		('category', [])             : 3 | ['season', 'weather', 'weekday']
		('float', [])                : 3 | ['temp', 'atemp', 'windspeed']
		('int', [])                  : 3 | ['humidity', 'week', 'hour']
		('int', ['bool'])            : 3 | ['holiday', 'workingday', 'year']
		('int', ['datetime_as_int']) : 5 | ['datetime', 'datetime.year', 'datetime.month', 'datetime.day', 'datetime.dayofweek']
	0.1s = Fit runtime
	13 features in original data used to generate 17 features in processed data.
	Train Data (Processed) Memory Usage: 1.02 MB (0.0% of available memory)
Data preprocessing and feature engineering runtime = 0.17s ...
AutoGluon will gauge predictive performance using evaluation metric: 'root_mean_squared_error'
	This metric's sign has been flipped to adhere to being higher_is_better. The metric score can be multiplied by -1 to get the metric value.
	To change this, specify the eval_metric parameter of Predictor()
AutoGluon will fit 2 stack levels (L1 to L2) ...
Fitting 2 L1 models ...
Hyperparameter tuning model: LightGBM_BAG_L1 ... Tuning model for up to 179.9s of the 599.83s of remaining time.

  0%|          | 0/10 [00:00<?, ?it/s]

	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
Fitted model: LightGBM_BAG_L1\T1 ...
	-48.1213	 = Validation score   (-root_mean_squared_error)
	16.37s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T2 ...
	-48.8559	 = Validation score   (-root_mean_squared_error)
	11.35s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T3 ...
	-41.4635	 = Validation score   (-root_mean_squared_error)
	11.06s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T4 ...
	-140.4194	 = Validation score   (-root_mean_squared_error)
	10.92s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T5 ...
	-52.1338	 = Validation score   (-root_mean_squared_error)
	11.05s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T6 ...
	-123.4752	 = Validation score   (-root_mean_squared_error)
	11.05s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T7 ...
	-48.7354	 = Validation score   (-root_mean_squared_error)
	11.04s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T8 ...
	-37.9529	 = Validation score   (-root_mean_squared_error)
	10.99s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T9 ...
	-131.3383	 = Validation score   (-root_mean_squared_error)
	10.87s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L1\T10 ...
	-39.8167	 = Validation score   (-root_mean_squared_error)
	10.85s	 = Training   runtime
	0.0s	 = Validation runtime
Hyperparameter tuning model: NeuralNetTorch_BAG_L1 ... Tuning model for up to 179.9s of the 482.89s of remaining time.
Warning: Exception caused NeuralNetTorch_BAG_L1 to fail during hyperparameter tuning... Skipping this model.
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\hyperopt\hyperopt_search.py", line 252, in _lookup
    idx = categories.index(config_dict[key])
ValueError: [100] is not in list

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\tuner.py", line 272, in fit
    return self._local_tuner.fit()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\impl\tuner_internal.py", line 420, in fit
    analysis = self._fit_internal(trainable, param_space)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\impl\tuner_internal.py", line 532, in _fit_internal
    analysis = run(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\tune.py", line 597, in run
    if config and not searcher_set_search_props(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\util.py", line 19, in _set_search_properties_backwards_compatible
    return set_search_properties_func(metric, mode, config, **spec)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\search_generator.py", line 63, in set_search_properties
    return _set_search_properties_backwards_compatible(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\util.py", line 19, in _set_search_properties_backwards_compatible
    return set_search_properties_func(metric, mode, config, **spec)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\hyperopt\hyperopt_search.py", line 292, in set_search_properties
    self._setup_hyperopt()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\hyperopt\hyperopt_search.py", line 222, in _setup_hyperopt
    self._convert_categories_to_indices(config)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\hyperopt\hyperopt_search.py", line 275, in _convert_categories_to_indices
    _lookup(config, self._space, k)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\hyperopt\hyperopt_search.py", line 271, in _lookup
    raise ValueError(msg) from exc
ValueError: Did not find category with value `[100]` in hyperopt parameter `layers`. Please make sure the specified category is valid.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\trainer\abstract_trainer.py", line 1761, in _train_single_full
    hpo_models, hpo_results = model.hyperparameter_tune(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 1257, in hyperparameter_tune
    return self._hyperparameter_tune(hpo_executor=hpo_executor, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 182, in _hyperparameter_tune
    return super()._hyperparameter_tune(X=X, y=y, k_fold=k_fold, hpo_executor=hpo_executor, preprocess_kwargs=preprocess_kwargs, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 1177, in _hyperparameter_tune
    hpo_executor.execute(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\hpo\executors.py", line 375, in execute
    analysis = run(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\hpo\ray_hpo.py", line 292, in run
    results = tuner.fit()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\tuner.py", line 274, in fit
    raise TuneError(
ray.tune.error.TuneError: The Ray Tune run failed. Please inspect the previous error messages for a cause. After fixing the issue, you can restart the run from scratch or continue this run. To continue this run, you can use `tuner = Tuner.restore("E:\online competition\kaggle\udacity_nd_bike_sharing_project\cd0385-project-starter\project\AutogluonModels\ag-20230531_043337\models\NeuralNetTorch_BAG_L1")`.
The Ray Tune run failed. Please inspect the previous error messages for a cause. After fixing the issue, you can restart the run from scratch or continue this run. To continue this run, you can use `tuner = Tuner.restore("E:\online competition\kaggle\udacity_nd_bike_sharing_project\cd0385-project-starter\project\AutogluonModels\ag-20230531_043337\models\NeuralNetTorch_BAG_L1")`.
Repeating k-fold bagging: 2/20
Fitting model: LightGBM_BAG_L1\T1 ... Training model for up to 282.4s of the 482.45s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-47.8427	 = Validation score   (-root_mean_squared_error)
	17.96s	 = Training   runtime
	0.1s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T2 ... Training model for up to 271.51s of the 471.55s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-48.4642	 = Validation score   (-root_mean_squared_error)
	12.95s	 = Training   runtime
	0.08s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T3 ... Training model for up to 260.6s of the 460.65s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-41.0288	 = Validation score   (-root_mean_squared_error)
	12.7s	 = Training   runtime
	0.11s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T4 ... Training model for up to 249.14s of the 449.19s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-140.404	 = Validation score   (-root_mean_squared_error)
	12.44s	 = Training   runtime
	0.06s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T5 ... Training model for up to 238.41s of the 438.45s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-51.9554	 = Validation score   (-root_mean_squared_error)
	12.65s	 = Training   runtime
	0.09s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T6 ... Training model for up to 227.63s of the 427.68s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-123.3835	 = Validation score   (-root_mean_squared_error)
	12.65s	 = Training   runtime
	0.08s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T7 ... Training model for up to 216.77s of the 416.82s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-48.3041	 = Validation score   (-root_mean_squared_error)
	12.58s	 = Training   runtime
	0.07s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T8 ... Training model for up to 206.06s of the 406.11s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-37.2628	 = Validation score   (-root_mean_squared_error)
	12.63s	 = Training   runtime
	0.12s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T9 ... Training model for up to 195.12s of the 395.16s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-131.3088	 = Validation score   (-root_mean_squared_error)
	12.39s	 = Training   runtime
	0.06s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T10 ... Training model for up to 184.29s of the 384.34s of remaining time.
	Fitting 8 child models (S2F1 - S2F8) | Fitting with ParallelLocalFoldFittingStrategy
	-38.9148	 = Validation score   (-root_mean_squared_error)
	12.38s	 = Training   runtime
	0.09s	 = Validation runtime
Repeating k-fold bagging: 3/20
Fitting model: LightGBM_BAG_L1\T1 ... Training model for up to 173.49s of the 373.53s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-47.6504	 = Validation score   (-root_mean_squared_error)
	19.62s	 = Training   runtime
	0.21s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T2 ... Training model for up to 162.54s of the 362.59s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-48.2846	 = Validation score   (-root_mean_squared_error)
	14.51s	 = Training   runtime
	0.16s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T3 ... Training model for up to 151.71s of the 351.75s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-40.8692	 = Validation score   (-root_mean_squared_error)
	14.36s	 = Training   runtime
	0.23s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T4 ... Training model for up to 140.59s of the 340.64s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-140.3918	 = Validation score   (-root_mean_squared_error)
	13.98s	 = Training   runtime
	0.14s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T5 ... Training model for up to 129.63s of the 329.67s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-51.8047	 = Validation score   (-root_mean_squared_error)
	14.27s	 = Training   runtime
	0.17s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T6 ... Training model for up to 118.66s of the 318.7s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-123.4192	 = Validation score   (-root_mean_squared_error)
	14.31s	 = Training   runtime
	0.16s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T7 ... Training model for up to 107.79s of the 307.83s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-48.112	 = Validation score   (-root_mean_squared_error)
	14.13s	 = Training   runtime
	0.15s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T8 ... Training model for up to 96.7s of the 296.74s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-37.024	 = Validation score   (-root_mean_squared_error)
	14.23s	 = Training   runtime
	0.24s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T9 ... Training model for up to 85.84s of the 285.88s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-131.313	 = Validation score   (-root_mean_squared_error)
	14.02s	 = Training   runtime
	0.13s	 = Validation runtime
Fitting model: LightGBM_BAG_L1\T10 ... Training model for up to 74.91s of the 274.95s of remaining time.
	Fitting 8 child models (S3F1 - S3F8) | Fitting with ParallelLocalFoldFittingStrategy
	-38.6076	 = Validation score   (-root_mean_squared_error)
	13.96s	 = Training   runtime
	0.18s	 = Validation runtime
Completed 3/20 k-fold bagging repeats ...
Fitting model: WeightedEnsemble_L2 ... Training model for up to 360.0s of the 263.65s of remaining time.
	-36.7956	 = Validation score   (-root_mean_squared_error)
	0.23s	 = Training   runtime
	0.0s	 = Validation runtime
Fitting 2 L2 models ...
Hyperparameter tuning model: LightGBM_BAG_L2 ... Tuning model for up to 118.53s of the 263.39s of remaining time.

  0%|          | 0/10 [00:00<?, ?it/s]

	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Fitting 8 child models (S1F1 - S1F8) | Fitting with ParallelLocalFoldFittingStrategy
	Stopping HPO to satisfy time limit...
Fitted model: LightGBM_BAG_L2\T1 ...
	-36.4404	 = Validation score   (-root_mean_squared_error)
	11.3s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T2 ...
	-36.172	 = Validation score   (-root_mean_squared_error)
	11.34s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T3 ...
	-36.4068	 = Validation score   (-root_mean_squared_error)
	11.44s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T4 ...
	-115.0644	 = Validation score   (-root_mean_squared_error)
	10.9s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T5 ...
	-37.7837	 = Validation score   (-root_mean_squared_error)
	11.46s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T6 ...
	-111.6776	 = Validation score   (-root_mean_squared_error)
	11.1s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T7 ...
	-36.2864	 = Validation score   (-root_mean_squared_error)
	11.29s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T8 ...
	-36.0603	 = Validation score   (-root_mean_squared_error)
	11.13s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T9 ...
	-103.007	 = Validation score   (-root_mean_squared_error)
	10.77s	 = Training   runtime
	0.0s	 = Validation runtime
Fitted model: LightGBM_BAG_L2\T10 ...
	-35.9819	 = Validation score   (-root_mean_squared_error)
	11.11s	 = Training   runtime
	0.0s	 = Validation runtime
Hyperparameter tuning model: NeuralNetTorch_BAG_L2 ... Tuning model for up to 118.53s of the 151.32s of remaining time.
Warning: Exception caused NeuralNetTorch_BAG_L2 to fail during hyperparameter tuning... Skipping this model.
Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\hyperopt\hyperopt_search.py", line 252, in _lookup
    idx = categories.index(config_dict[key])
ValueError: [100] is not in list

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\tuner.py", line 272, in fit
    return self._local_tuner.fit()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\impl\tuner_internal.py", line 420, in fit
    analysis = self._fit_internal(trainable, param_space)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\impl\tuner_internal.py", line 532, in _fit_internal
    analysis = run(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\tune.py", line 597, in run
    if config and not searcher_set_search_props(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\util.py", line 19, in _set_search_properties_backwards_compatible
    return set_search_properties_func(metric, mode, config, **spec)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\search_generator.py", line 63, in set_search_properties
    return _set_search_properties_backwards_compatible(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\util.py", line 19, in _set_search_properties_backwards_compatible
    return set_search_properties_func(metric, mode, config, **spec)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\hyperopt\hyperopt_search.py", line 292, in set_search_properties
    self._setup_hyperopt()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\hyperopt\hyperopt_search.py", line 222, in _setup_hyperopt
    self._convert_categories_to_indices(config)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\hyperopt\hyperopt_search.py", line 275, in _convert_categories_to_indices
    _lookup(config, self._space, k)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\search\hyperopt\hyperopt_search.py", line 271, in _lookup
    raise ValueError(msg) from exc
ValueError: Did not find category with value `[100]` in hyperopt parameter `layers`. Please make sure the specified category is valid.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\trainer\abstract_trainer.py", line 1761, in _train_single_full
    hpo_models, hpo_results = model.hyperparameter_tune(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\abstract\abstract_model.py", line 1257, in hyperparameter_tune
    return self._hyperparameter_tune(hpo_executor=hpo_executor, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\stacker_ensemble_model.py", line 182, in _hyperparameter_tune
    return super()._hyperparameter_tune(X=X, y=y, k_fold=k_fold, hpo_executor=hpo_executor, preprocess_kwargs=preprocess_kwargs, **kwargs)
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\models\ensemble\bagged_ensemble_model.py", line 1177, in _hyperparameter_tune
    hpo_executor.execute(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\hpo\executors.py", line 375, in execute
    analysis = run(
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\autogluon\core\hpo\ray_hpo.py", line 292, in run
    results = tuner.fit()
  File "C:\Users\Chris\anaconda3\envs\py38_base\lib\site-packages\ray\tune\tuner.py", line 274, in fit
    raise TuneError(
ray.tune.error.TuneError: The Ray Tune run failed. Please inspect the previous error messages for a cause. After fixing the issue, you can restart the run from scratch or continue this run. To continue this run, you can use `tuner = Tuner.restore("E:\online competition\kaggle\udacity_nd_bike_sharing_project\cd0385-project-starter\project\AutogluonModels\ag-20230531_043337\models\NeuralNetTorch_BAG_L2")`.
The Ray Tune run failed. Please inspect the previous error messages for a cause. After fixing the issue, you can restart the run from scratch or continue this run. To continue this run, you can use `tuner = Tuner.restore("E:\online competition\kaggle\udacity_nd_bike_sharing_project\cd0385-project-starter\project\AutogluonModels\ag-20230531_043337\models\NeuralNetTorch_BAG_L2")`.
Completed 1/20 k-fold bagging repeats ...
Fitting model: WeightedEnsemble_L3 ... Training model for up to 360.0s of the 151.22s of remaining time.
	-35.7741	 = Validation score   (-root_mean_squared_error)
	0.26s	 = Training   runtime
	0.0s	 = Validation runtime
AutoGluon training complete, total runtime = 449.07s ... Best model: "WeightedEnsemble_L3"
TabularPredictor saved. To load, use: predictor = TabularPredictor.load("AutogluonModels\ag-20230531_043337\")

predictor_new_hpo2.fit_summary()

*** Summary of fit() ***
Estimated performance of each model:
                  model   score_val  pred_time_val    fit_time  pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  fit_order
0   WeightedEnsemble_L3  -35.774051       1.772058  181.241197                0.000999           0.263998            3       True         22
1   LightGBM_BAG_L2\T10  -35.981921       1.771059  158.507892                0.001000          11.113278            2       True         21
2    LightGBM_BAG_L2\T8  -36.060335       1.770059  158.524888                0.000000          11.130274            2       True         19
3    LightGBM_BAG_L2\T2  -36.171994       1.770059  158.733648                0.000000          11.339034            2       True         13
4    LightGBM_BAG_L2\T7  -36.286430       1.770059  158.686630                0.000000          11.292016            2       True         18
5    LightGBM_BAG_L2\T3  -36.406820       1.770059  158.835299                0.000000          11.440685            2       True         14
6    LightGBM_BAG_L2\T1  -36.440448       1.770059  158.692754                0.000000          11.298140            2       True         12
7   WeightedEnsemble_L2  -36.795580       0.418004   28.422191                0.001000           0.230996            2       True         11
8    LightGBM_BAG_L1\T8  -37.024016       0.236002   14.231187                0.236002          14.231187            1       True          8
9    LightGBM_BAG_L2\T5  -37.783677       1.770059  158.849647                0.000000          11.455033            2       True         16
10  LightGBM_BAG_L1\T10  -38.607579       0.181001   13.960008                0.181001          13.960008            1       True         10
11   LightGBM_BAG_L1\T3  -40.869191       0.234013   14.358388                0.234013          14.358388            1       True          3
12   LightGBM_BAG_L1\T1  -47.650433       0.205012   19.618656                0.205012          19.618656            1       True          1
13   LightGBM_BAG_L1\T7  -48.111992       0.153008   14.131077                0.153008          14.131077            1       True          7
14   LightGBM_BAG_L1\T2  -48.284649       0.161995   14.505001                0.161995          14.505001            1       True          2
15   LightGBM_BAG_L1\T5  -51.804726       0.172031   14.274050                0.172031          14.274050            1       True          5
16   LightGBM_BAG_L2\T9 -103.007016       1.770059  158.161762                0.000000          10.767148            2       True         20
17   LightGBM_BAG_L2\T6 -111.677585       1.770059  158.498611                0.000000          11.103997            2       True         17
18   LightGBM_BAG_L2\T4 -115.064413       1.770059  158.293782                0.000000          10.899168            2       True         15
19   LightGBM_BAG_L1\T6 -123.419154       0.162997   14.314400                0.162997          14.314400            1       True          6
20   LightGBM_BAG_L1\T9 -131.312991       0.126005   14.018013                0.126005          14.018013            1       True          9
21   LightGBM_BAG_L1\T4 -140.391777       0.137994   13.983833                0.137994          13.983833            1       True          4
Number of models trained: 22
Types of models trained:
{'WeightedEnsembleModel', 'StackerEnsembleModel_LGB'}
Bagging used: True  (with 8 folds)
Multi-layer stack-ensembling used: True  (with 3 levels)
Feature Metadata (Processed):
(raw dtype, special dtypes):
('category', [])             : 3 | ['season', 'weather', 'weekday']
('float', [])                : 3 | ['temp', 'atemp', 'windspeed']
('int', [])                  : 3 | ['humidity', 'week', 'hour']
('int', ['bool'])            : 3 | ['holiday', 'workingday', 'year']
('int', ['datetime_as_int']) : 5 | ['datetime', 'datetime.year', 'datetime.month', 'datetime.day', 'datetime.dayofweek']
*** End of fit() summary ***

{'model_types': {'LightGBM_BAG_L1\\T1': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T2': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T3': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T4': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T5': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T6': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T7': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T8': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T9': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L1\\T10': 'StackerEnsembleModel_LGB',
  'WeightedEnsemble_L2': 'WeightedEnsembleModel',
  'LightGBM_BAG_L2\\T1': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T2': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T3': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T4': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T5': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T6': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T7': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T8': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T9': 'StackerEnsembleModel_LGB',
  'LightGBM_BAG_L2\\T10': 'StackerEnsembleModel_LGB',
  'WeightedEnsemble_L3': 'WeightedEnsembleModel'},
 'model_performance': {'LightGBM_BAG_L1\\T1': -47.650432794522196,
  'LightGBM_BAG_L1\\T2': -48.28464931909125,
  'LightGBM_BAG_L1\\T3': -40.86919096387156,
  'LightGBM_BAG_L1\\T4': -140.39177699464057,
  'LightGBM_BAG_L1\\T5': -51.80472626835246,
  'LightGBM_BAG_L1\\T6': -123.41915363718512,
  'LightGBM_BAG_L1\\T7': -48.111991913771384,
  'LightGBM_BAG_L1\\T8': -37.02401631024006,
  'LightGBM_BAG_L1\\T9': -131.31299067162985,
  'LightGBM_BAG_L1\\T10': -38.607578808884156,
  'WeightedEnsemble_L2': -36.79558000753171,
  'LightGBM_BAG_L2\\T1': -36.440448487671716,
  'LightGBM_BAG_L2\\T2': -36.17199449477448,
  'LightGBM_BAG_L2\\T3': -36.40682028374784,
  'LightGBM_BAG_L2\\T4': -115.06441262162491,
  'LightGBM_BAG_L2\\T5': -37.78367715761663,
  'LightGBM_BAG_L2\\T6': -111.6775845548824,
  'LightGBM_BAG_L2\\T7': -36.28643017794523,
  'LightGBM_BAG_L2\\T8': -36.06033513523615,
  'LightGBM_BAG_L2\\T9': -103.00701583912745,
  'LightGBM_BAG_L2\\T10': -35.98192125320506,
  'WeightedEnsemble_L3': -35.774050913898265},
 'model_best': 'WeightedEnsemble_L3',
 'model_paths': {'LightGBM_BAG_L1\\T1': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L1\\T1\\',
  'LightGBM_BAG_L1\\T2': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L1\\T2\\',
  'LightGBM_BAG_L1\\T3': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L1\\T3\\',
  'LightGBM_BAG_L1\\T4': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L1\\T4\\',
  'LightGBM_BAG_L1\\T5': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L1\\T5\\',
  'LightGBM_BAG_L1\\T6': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L1\\T6\\',
  'LightGBM_BAG_L1\\T7': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L1\\T7\\',
  'LightGBM_BAG_L1\\T8': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L1\\T8\\',
  'LightGBM_BAG_L1\\T9': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L1\\T9\\',
  'LightGBM_BAG_L1\\T10': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L1\\T10\\',
  'WeightedEnsemble_L2': 'AutogluonModels\\ag-20230531_043337\\models\\WeightedEnsemble_L2\\',
  'LightGBM_BAG_L2\\T1': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L2\\T1\\',
  'LightGBM_BAG_L2\\T2': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L2\\T2\\',
  'LightGBM_BAG_L2\\T3': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L2\\T3\\',
  'LightGBM_BAG_L2\\T4': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L2\\T4\\',
  'LightGBM_BAG_L2\\T5': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L2\\T5\\',
  'LightGBM_BAG_L2\\T6': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L2\\T6\\',
  'LightGBM_BAG_L2\\T7': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L2\\T7\\',
  'LightGBM_BAG_L2\\T8': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L2\\T8\\',
  'LightGBM_BAG_L2\\T9': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L2\\T9\\',
  'LightGBM_BAG_L2\\T10': 'E:\\online competition\\kaggle\\udacity_nd_bike_sharing_project\\cd0385-project-starter\\project\\AutogluonModels\\ag-20230531_043337\\models\\LightGBM_BAG_L2\\T10\\',
  'WeightedEnsemble_L3': 'AutogluonModels\\ag-20230531_043337\\models\\WeightedEnsemble_L3\\'},
 'model_fit_times': {'LightGBM_BAG_L1\\T1': 19.618656158447266,
  'LightGBM_BAG_L1\\T2': 14.505001068115234,
  'LightGBM_BAG_L1\\T3': 14.358388423919678,
  'LightGBM_BAG_L1\\T4': 13.983833312988281,
  'LightGBM_BAG_L1\\T5': 14.274049997329712,
  'LightGBM_BAG_L1\\T6': 14.314399719238281,
  'LightGBM_BAG_L1\\T7': 14.131077289581299,
  'LightGBM_BAG_L1\\T8': 14.231187105178833,
  'LightGBM_BAG_L1\\T9': 14.018013000488281,
  'LightGBM_BAG_L1\\T10': 13.960007905960083,
  'WeightedEnsemble_L2': 0.23099565505981445,
  'LightGBM_BAG_L2\\T1': 11.298139810562134,
  'LightGBM_BAG_L2\\T2': 11.339033842086792,
  'LightGBM_BAG_L2\\T3': 11.44068455696106,
  'LightGBM_BAG_L2\\T4': 10.899168252944946,
  'LightGBM_BAG_L2\\T5': 11.455033302307129,
  'LightGBM_BAG_L2\\T6': 11.103997230529785,
  'LightGBM_BAG_L2\\T7': 11.292015552520752,
  'LightGBM_BAG_L2\\T8': 11.130273580551147,
  'LightGBM_BAG_L2\\T9': 10.767148494720459,
  'LightGBM_BAG_L2\\T10': 11.113278150558472,
  'WeightedEnsemble_L3': 0.26399779319763184},
 'model_pred_times': {'LightGBM_BAG_L1\\T1': 0.20501208305358887,
  'LightGBM_BAG_L1\\T2': 0.16199493408203125,
  'LightGBM_BAG_L1\\T3': 0.23401331901550293,
  'LightGBM_BAG_L1\\T4': 0.13799357414245605,
  'LightGBM_BAG_L1\\T5': 0.17203116416931152,
  'LightGBM_BAG_L1\\T6': 0.16299748420715332,
  'LightGBM_BAG_L1\\T7': 0.15300798416137695,
  'LightGBM_BAG_L1\\T8': 0.23600172996520996,
  'LightGBM_BAG_L1\\T9': 0.12600493431091309,
  'LightGBM_BAG_L1\\T10': 0.1810014247894287,
  'WeightedEnsemble_L2': 0.0010004043579101562,
  'LightGBM_BAG_L2\\T1': 0.0,
  'LightGBM_BAG_L2\\T2': 0.0,
  'LightGBM_BAG_L2\\T3': 0.0,
  'LightGBM_BAG_L2\\T4': 0.0,
  'LightGBM_BAG_L2\\T5': 0.0,
  'LightGBM_BAG_L2\\T6': 0.0,
  'LightGBM_BAG_L2\\T7': 0.0,
  'LightGBM_BAG_L2\\T8': 0.0,
  'LightGBM_BAG_L2\\T9': 0.0,
  'LightGBM_BAG_L2\\T10': 0.0010001659393310547,
  'WeightedEnsemble_L3': 0.0009989738464355469},
 'num_bag_folds': 8,
 'max_stack_level': 3,
 'model_hyperparams': {'LightGBM_BAG_L1\\T1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T3': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T4': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T5': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T6': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T7': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T8': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T9': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L1\\T10': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'WeightedEnsemble_L2': {'use_orig_features': False,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T1': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T2': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T3': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T4': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T5': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T6': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T7': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T8': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T9': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'LightGBM_BAG_L2\\T10': {'use_orig_features': True,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True},
  'WeightedEnsemble_L3': {'use_orig_features': False,
   'max_base_models': 25,
   'max_base_models_per_type': 5,
   'save_bag_folds': True}},
 'leaderboard':                   model   score_val  pred_time_val    fit_time  \
 0   WeightedEnsemble_L3  -35.774051       1.772058  181.241197   
 1   LightGBM_BAG_L2\T10  -35.981921       1.771059  158.507892   
 2    LightGBM_BAG_L2\T8  -36.060335       1.770059  158.524888   
 3    LightGBM_BAG_L2\T2  -36.171994       1.770059  158.733648   
 4    LightGBM_BAG_L2\T7  -36.286430       1.770059  158.686630   
 5    LightGBM_BAG_L2\T3  -36.406820       1.770059  158.835299   
 6    LightGBM_BAG_L2\T1  -36.440448       1.770059  158.692754   
 7   WeightedEnsemble_L2  -36.795580       0.418004   28.422191   
 8    LightGBM_BAG_L1\T8  -37.024016       0.236002   14.231187   
 9    LightGBM_BAG_L2\T5  -37.783677       1.770059  158.849647   
 10  LightGBM_BAG_L1\T10  -38.607579       0.181001   13.960008   
 11   LightGBM_BAG_L1\T3  -40.869191       0.234013   14.358388   
 12   LightGBM_BAG_L1\T1  -47.650433       0.205012   19.618656   
 13   LightGBM_BAG_L1\T7  -48.111992       0.153008   14.131077   
 14   LightGBM_BAG_L1\T2  -48.284649       0.161995   14.505001   
 15   LightGBM_BAG_L1\T5  -51.804726       0.172031   14.274050   
 16   LightGBM_BAG_L2\T9 -103.007016       1.770059  158.161762   
 17   LightGBM_BAG_L2\T6 -111.677585       1.770059  158.498611   
 18   LightGBM_BAG_L2\T4 -115.064413       1.770059  158.293782   
 19   LightGBM_BAG_L1\T6 -123.419154       0.162997   14.314400   
 20   LightGBM_BAG_L1\T9 -131.312991       0.126005   14.018013   
 21   LightGBM_BAG_L1\T4 -140.391777       0.137994   13.983833   
 
     pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  \
 0                 0.000999           0.263998            3       True   
 1                 0.001000          11.113278            2       True   
 2                 0.000000          11.130274            2       True   
 3                 0.000000          11.339034            2       True   
 4                 0.000000          11.292016            2       True   
 5                 0.000000          11.440685            2       True   
 6                 0.000000          11.298140            2       True   
 7                 0.001000           0.230996            2       True   
 8                 0.236002          14.231187            1       True   
 9                 0.000000          11.455033            2       True   
 10                0.181001          13.960008            1       True   
 11                0.234013          14.358388            1       True   
 12                0.205012          19.618656            1       True   
 13                0.153008          14.131077            1       True   
 14                0.161995          14.505001            1       True   
 15                0.172031          14.274050            1       True   
 16                0.000000          10.767148            2       True   
 17                0.000000          11.103997            2       True   
 18                0.000000          10.899168            2       True   
 19                0.162997          14.314400            1       True   
 20                0.126005          14.018013            1       True   
 21                0.137994          13.983833            1       True   
 
     fit_order  
 0          22  
 1          21  
 2          19  
 3          13  
 4          18  
 5          14  
 6          12  
 7          11  
 8           8  
 9          16  
 10         10  
 11          3  
 12          1  
 13          7  
 14          2  
 15          5  
 16         20  
 17         17  
 18         15  
 19          6  
 20          9  
 21          4  }

predictions_new_features_hpo2 = predictor_new_hpo2.predict(test,model=predictor_new_hpo2.get_model_best())
predictions_new_features_hpo2.head()

0    10.651279
1     6.327431
2     6.279728
3     6.315984
4     6.302880
Name: count, dtype: float32

# Remember to set all negative values to zero
predictions_new_features_hpo2.describe()

count    6493.000000
mean      190.663055
std       174.672501
min         5.210919
25%        43.650482
50%       148.237976
75%       283.945831
max       877.211304
Name: count, dtype: float64

predictions_new_features_hpo2[predictions_new_features_hpo2<0].count()

0

predictions_new_features_hpo2[predictions_new_features_hpo2<0]=0

submission_new_hpo2 = submission.copy(deep=True)

# Same submitting predictions
submission_new_hpo2["count"] = predictions_new_features_hpo2
submission_new_hpo2.to_csv("submission_new_hpo2.csv", index=False)

!kaggle competitions submit -c bike-sharing-demand -f submission_new_hpo2.csv -m "new features with hyperparameters2"

Successfully submitted to Bike Sharing Demand

  0%|          | 0.00/194k [00:00<?, ?B/s]
  4%|4         | 8.00k/194k [00:00<00:05, 32.1kB/s]
 95%|#########4| 184k/194k [00:00<00:00, 628kB/s]  
100%|##########| 194k/194k [00:04<00:00, 40.8kB/s]

!kaggle competitions submissions -c bike-sharing-demand 
#| tail -n +1 | head -n 6

fileName                     date                 description                         status    publicScore  privateScore  
---------------------------  -------------------  ----------------------------------  --------  -----------  ------------  
submission_new_hpo2.csv      2023-05-31 04:42:10  new features with hyperparameters2  complete  0.46765      0.46765       
submission_new_hpo1.csv      2023-05-31 03:08:31  new features with hyperparameters1  complete  0.46803      0.46803       
submission_new_hpo.csv       2023-05-31 01:32:59                                      complete  0.49844      0.49844       
submission_new_hpo.csv       2023-05-31 00:59:18  new features with hyperparameters   complete  0.49844      0.49844       
submission_new_features.csv  2023-05-30 06:32:08  new features                        complete  0.70588      0.70588       
submission.csv               2023-05-30 05:49:46  first raw submission                complete  1.80425      1.80425       

New Score of 0.46765

Step 7: Write a Report

Refer to the markdown file for the full report

Creating plots and table for report

baseline_leaderboard=predictor.leaderboard()
newfeatures_leaderboard=predictor_new_features.leaderboard()
hpo_leaderboard1=predictor_new_hpo.leaderboard()
hpo_leaderboard2=predictor_new_hpo1.leaderboard()
hpo_leaderboard3=predictor_new_hpo2.leaderboard()

                  model   score_val  pred_time_val    fit_time  pred_time_val_marginal  fit_time_marginal  stack_level  can_infer  fit_order
0   WeightedEnsemble_L3  -35.774051       1.772058  181.241197                0.000999           0.263998            3       True         22
1   LightGBM_BAG_L2\T10  -35.981921       1.771059  158.507892                0.001000          11.113278            2       True         21
2    LightGBM_BAG_L2\T8  -36.060335       1.770059  158.524888                0.000000          11.130274            2       True         19
3    LightGBM_BAG_L2\T2  -36.171994       1.770059  158.733648                0.000000          11.339034            2       True         13
4    LightGBM_BAG_L2\T7  -36.286430       1.770059  158.686630                0.000000          11.292016            2       True         18
5    LightGBM_BAG_L2\T3  -36.406820       1.770059  158.835299                0.000000          11.440685            2       True         14
6    LightGBM_BAG_L2\T1  -36.440448       1.770059  158.692754                0.000000          11.298140            2       True         12
7   WeightedEnsemble_L2  -36.795580       0.418004   28.422191                0.001000           0.230996            2       True         11
8    LightGBM_BAG_L1\T8  -37.024016       0.236002   14.231187                0.236002          14.231187            1       True          8
9    LightGBM_BAG_L2\T5  -37.783677       1.770059  158.849647                0.000000          11.455033            2       True         16
10  LightGBM_BAG_L1\T10  -38.607579       0.181001   13.960008                0.181001          13.960008            1       True         10
11   LightGBM_BAG_L1\T3  -40.869191       0.234013   14.358388                0.234013          14.358388            1       True          3
12   LightGBM_BAG_L1\T1  -47.650433       0.205012   19.618656                0.205012          19.618656            1       True          1
13   LightGBM_BAG_L1\T7  -48.111992       0.153008   14.131077                0.153008          14.131077            1       True          7
14   LightGBM_BAG_L1\T2  -48.284649       0.161995   14.505001                0.161995          14.505001            1       True          2
15   LightGBM_BAG_L1\T5  -51.804726       0.172031   14.274050                0.172031          14.274050            1       True          5
16   LightGBM_BAG_L2\T9 -103.007016       1.770059  158.161762                0.000000          10.767148            2       True         20
17   LightGBM_BAG_L2\T6 -111.677585       1.770059  158.498611                0.000000          11.103997            2       True         17
18   LightGBM_BAG_L2\T4 -115.064413       1.770059  158.293782                0.000000          10.899168            2       True         15
19   LightGBM_BAG_L1\T6 -123.419154       0.162997   14.314400                0.162997          14.314400            1       True          6
20   LightGBM_BAG_L1\T9 -131.312991       0.126005   14.018013                0.126005          14.018013            1       True          9
21   LightGBM_BAG_L1\T4 -140.391777       0.137994   13.983833                0.137994          13.983833            1       True          4

baseline_model_score = abs(baseline_leaderboard['score_val'][0]) #50.545607#
newfeatures_model_score = abs(newfeatures_leaderboard['score_val'][0]) #29.890078#
hpo_model_score1 = abs(hpo_leaderboard1['score_val'][0]) #32.375607#
hpo_model_score2 = abs(hpo_leaderboard2['score_val'][0]) #36.428313#
hpo_model_score3 = abs(hpo_leaderboard3['score_val'][0]) #35.774051#

# Taking the top model score from each training run and creating a line plot to show improvement
# You can create these in the notebook and save them to PNG or use some other tool (e.g. google sheets, excel)
fig = pd.DataFrame(
    {
        "model": ["initial", "add_features", "hpo1","hpo2","hpo3"],
        "score": [baseline_model_score,newfeatures_model_score,hpo_model_score1,hpo_model_score2,hpo_model_score3]
    }
).plot(x="model", y="score",  ylabel= 'RMSE', style='-*', grid=True, figsize=(8, 6)).get_figure()
fig.savefig('img/model_train_score.png')

# Take the 3 kaggle scores and creating a line plot to show improvement
fig = pd.DataFrame(
    {
        "test_eval": ["initial", "add_features", "hpo1","hpo2","hpo3"],
        "score": [1.80425, 0.70588, 0.49844, 0.46803, 0.46765]
    }
).plot(x="test_eval", y="score", ylabel= 'RMSLE',style='-*',grid=True,figsize=(8, 6)).get_figure()

fig.savefig('img/model_test_score.png')

Hyperparameter table

# The 3 hyperparameters we tuned with the kaggle score as the result
pd.DataFrame({
    "model": ["initial", "add_features", "hpo","hpo1","hpo2"],
    "hpo1": ['default', 'default', 'auto',
             "GBM: num_boost_round=80, num_leaves(lower=10, upper=50, default=20)",
             "GBM: num_boost_round=80, num_leaves(lower=10, upper=50, default=20)"],
    "hpo2": ['default', 'default', 'auto',
             "NN_TORCH: num_epochs=10, learning_rate(1e-3, 1e-2, default=5e-3, log=True),activation('relu', 'softrelu', 'tanh'),layers([100],[200, 100])",
             "NN_TORCH: num_epochs(lower=8, upper=20, default=10), learning_rate(1e-3, 1e-2, default=5e-3, log=True),activation('relu', 'softrelu', 'tanh'),layers([100],[1000],[200, 100])"],
    "scheduler": ['default', 'default', 'ASHA','local','local'],
    "trial_time(seconds)": [600, 600,600,600,600],
    "score": [1.80425, 0.70588, 0.49844, 0.46803, 0.46765]
})

	model	hpo1	hpo2	scheduler	trial_time(seconds)	score
0	initial	default	default	default	600	1.80425
1	add_features	default	default	default	600	0.70588
2	hpo	auto	auto	ASHA	600	0.49844
3	hpo1	GBM: num_boost_round=80, num_leaves(lower=10, ...	NN_TORCH: num_epochs=10, learning_rate(1e-3, 1...	local	600	0.46803
4	hpo2	GBM: num_boost_round=80, num_leaves(lower=10, ...	NN_TORCH: num_epochs(lower=8, upper=20, defaul...	local	600	0.46765

Report: Predict Bike Sharing Demand with AutoGluon Solution

Noman Arshad

Initial Training

What did you realize when you tried to submit your predictions? What changes were needed to the output of the predictor to submit your results?

The output column (count - number of total rentals) should not be less than 0 as count can not be negative. So before submiting predictions we need to make sure that our predictions does not contain any negative value in predicted count.

What was the top ranked model that performed?

WeightedEnsemble_L2 with feature engineering and Hyper parameter optimization.

Exploratory data analysis and feature creation

What did the exploratory analysis find and how did you add additional features?

I checked correlation matrix of train df and found that initialy most correlated column was temp and realized that temp is not constant for every hour in a day and also for every week might have different avg temp. So I created some additional columns based on datetime provided to fetch hour of day, week of year, weekday etc. and it really helped in improving model performance.

How much better did your model preform after adding additional features and why do you think that is?

Model improved significantly after adding new features. I think it is due to the quality of feature. By adding creating highly correlated feature it helps model to learn better and find better decision boundary.

Hyper parameter tuning

How much better did your model preform after trying different hyper parameters?

Model performance improved with hyper parameter optimization but not that much as it improved by adding new features. From score table you can see by adding new features it improved significantly from 1.8 RMSLE to 0.7, and after HPO it improved by 0.2 RMSLE further.

If you were given more time with this dataset, where do you think you would spend more time?

I would like to spend more time on feature engineering to create new useful features that help model to learn decision boundary for better accuracy. With this I would also like to play with hyperparameters.

Create a table with the models you ran, the hyperparameters modified, and the kaggle score.

model	hpo1	hpo2	scheduler	trial_time (seconds)	score
initial	default	default	default	600	1.80425
add_features	default	default	default	600	0.70588
hpo	auto	auto	ASHA	600	0.49844
hpo1	GBM: num_boost_round=80, num_leaves(lower=10, upper=50, default=20)	NN_TORCH: num_epochs=10, learning_rate(1e-3, 1e-2, default=5e-3, log=True),activation('relu', 'softrelu', 'tanh'),layers([100],[200, 100])	local	600	0.46803
hpo2	GBM: num_boost_round=80, num_leaves(lower=10, upper=50, default=20)	NN_TORCH: num_epochs(lower=8, upper=20, default=10), learning_rate(1e-3, 1e-2, default=5e-3, log=True),activation('relu', 'softrelu', 'tanh'),layers([100],[1000],[200, 100])	local	600	0.46803

Create a line plot showing the top model score for the three (or more) training runs during the project.

Create a line plot showing the top kaggle score for the three (or more) prediction submissions during the project.

Summary

We can improve model performance by spending time on EDA and feature engineering. With better features we can train better models. After training model on data we can then fine tune model by playing with its hyper parameters.

References:

• https://auto.gluon.ai/dev/tutorials/multimodal/advanced_topics/hyperparameter_optimization.html
• https://docs.aws.amazon.com/sagemaker/latest/dg/autogluon-tabular-hyperparameters.html